© 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. 2-RES-SM
    11. 14056
    Prev
    Next
    INDEX
    Explanations

    references to software and programming components

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    263
    +0.18
    1.0%
    63
    +0.14
    0.8%
    83
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.18
    0.04
    63
    +0.14
    0.07
    263
    +0.12
    0.15
    Negative Logits
    Ħ
    -1.92
    ľĵ
    -1.85
    »
    -1.80
    £
    -1.77
    Ŀ
    -1.77
    ¿½
    -1.69
    ģ
    -1.66
    ±
    -1.66
    ĻĤ
    -1.65
    Ľ
    -1.63
    POSITIVE LOGITS
    ishly
    1.70
    matically
    1.61
    ically
    1.56
     royalty
    1.53
     duty
    1.46
    hee
    1.43
     myself
    1.39
    ored
    1.38
    ually
    1.38
    led
    1.37
    Activations Density 4.619%

    No Known Activations