© 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. 1-RES-SM
    11. 29834
    Prev
    Next
    INDEX
    Explanations

    occurrences of utility-related terms in the text

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    392
    +0.18
    1.0%
    438
    +0.14
    0.8%
    376
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.18
    0.04
    379
    +0.14
    0.03
    438
    +0.13
    0.02
    Negative Logits
    ees
    -2.15
    ces
    -1.69
    irs
    -1.66
    FORE
    -1.64
    than
    -1.59
    rils
    -1.58
    ee
    -1.49
    esi
    -1.40
    cip
    -1.39
    few
    -1.39
    POSITIVE LOGITS
    ¥
    2.15
    ®
    1.98
    ½
    1.89
    £
    1.82
    ¤
    1.79
    º
    1.72
    ĭ
    1.69
    ister
    1.68
    Ļª
    1.62
     sake
    1.61
    Activations Density 0.179%

    No Known Activations