© 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. 14322
    Prev
    Next
    INDEX
    Explanations

    phrases indicating additional information or context

    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
    21
    +0.23
    1.3%
    421
    +0.11
    0.7%
    194
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.23
    0.02
    308
    +0.11
    0.02
    421
    +0.11
    0.02
    Negative Logits
    ī
    -3.15
    Ĥ
    -3.08
    ĥ
    -2.88
    Ģ
    -2.87
    Ħ
    -2.77
    ľĵ
    -2.77
    Īĺ
    -2.77
    ĨĴ
    -2.75
    ¿
    -2.73
    Ĥ¬
    -2.72
    POSITIVE LOGITS
     thereto
    2.54
     to
    2.28
    to
    1.75
    áŁ
    1.52
    blockList
    1.47
    going
    1.45
    urate
    1.44
     there
    1.42
    To
    1.32
     latitude
    1.31
    Activations Density 0.093%

    No Known Activations