© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 15042
    Prev
    Next
    INDEX
    Explanations

    references to generational expectations and values, particularly regarding diversity and inclusion in the workplace

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    21
    +0.33
    2.1%
    306
    +0.15
    0.9%
    292
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.33
    0.04
    261
    +0.15
    0.05
    18
    +0.10
    0.07
    Negative Logits
     values
    -1.49
     digits
    -1.47
     worse
    -1.38
     designate
    -1.35
    ille
    -1.30
    ,^[@
    -1.30
    izontal
    -1.26
    illa
    -1.26
     value
    -1.23
     worst
    -1.23
    POSITIVE LOGITS
    ================================
    1.57
    ===========================
    1.48
    =================
    1.47
    =================================
    1.46
    ========================
    1.46
    ================================================
    1.44
    -------------------------------------------------
    1.41
    -------------------------------------
    1.41
    ~~~~~~~~~~~~~~~~
    1.41
    ================
    1.41
    Activations Density 0.317%

    No Known Activations