© 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 EvalsExportsAPI 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. 12950
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structures

    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
    397
    +0.31
    1.9%
    21
    +0.19
    1.2%
    78
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.31
    0.15
    78
    +0.19
    0.01
    37
    +0.13
    0.01
    Negative Logits
    ');
    -2.23
    ");
    -2.15
    \",
    -2.02
    '):
    -2.01
    ”,
    -1.83
    ¿½
    -1.78
    \]),
    -1.77
    '),
    -1.71
    ’,
    -1.70
    *),
    -1.68
    POSITIVE LOGITS
    ↵↵
    2.30
    ↵	↵
    2.26
    ↵
    2.20
    č↵č
    2.19
    ↵↵↵↵
    2.12
    č↵č↵č
    2.06
     {#
    2.05
    ↵↵↵↵↵↵↵
    1.99
     ↵↵
    1.97
    ↵ ↵
    1.90
    Activations Density 1.822%

    No Known Activations