© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14364
    Prev
    Next
    INDEX
    Explanations

    key terms related to software packages and metadata

    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
    156
    +0.21
    1.2%
    78
    +0.19
    1.1%
    9
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.21
    0.11
    78
    +0.19
    0.01
    9
    +0.15
    0.11
    Negative Logits
    .",
    -1.74
    ;}
    -1.72
    ;"
    -1.64
    )",
    -1.63
    )',
    -1.62
    ;,
    -1.57
    .);
    -1.54
     beating
    -1.50
    ;</
    -1.49
    than
    -1.47
    POSITIVE LOGITS
    Ļª
    3.29
    ¢
    3.24
    ŀ
    3.14
    ģ
    2.98
    ¡
    2.97
    ¦
    2.96
    ¥
    2.95
    Ķ
    2.94
    Ŀ
    2.93
    «
    2.92
    Activations Density 1.704%

    No Known Activations