© 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. 9698
    Prev
    Next
    INDEX
    Explanations

    statements indicating importance or relevance

    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
    78
    +0.23
    1.4%
    348
    +0.19
    1.1%
    306
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.08
    236
    +0.19
    0.06
    348
    +0.13
    0.04
    Negative Logits
    Īĺ
    -2.31
    ¼
    -2.29
    »¿
    -2.22
    ¶
    -2.12
    ĥ½
    -2.08
    ľĵ
    -2.04
              ↵
    -2.02
    -2.02
    <|outofrange|>
    -2.02
    ↵
    -2.02
    POSITIVE LOGITS
     partly
    2.12
     true
    1.89
     point
    1.85
     paradox
    1.82
     empirically
    1.74
     emphas
    1.74
     exemplified
    1.73
     particularly
    1.72
     why
    1.72
     borne
    1.68
    Activations Density 0.855%

    No Known Activations