© 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. 14533
    Prev
    Next
    INDEX
    Explanations

    assertions of influence or impact

    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
    307
    +0.15
    0.9%
    447
    +0.12
    0.7%
    286
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.15
    0.06
    485
    +0.12
    0.04
    314
    +0.12
    0.06
    Negative Logits
    İ
    -2.45
    ¸
    -2.29
    ij
    -2.17
    ¬
    -2.02
    ī
    -1.89
    ¿½
    -1.89
    ¦
    -1.88
    ª
    -1.85
    «
    -1.82
    ĨĴ
    -1.81
    POSITIVE LOGITS
    hift
    3.29
     them
    2.07
     sense
    2.06
     headlines
    2.01
    estly
    1.96
    leine
    1.76
     sure
    1.76
     him
    1.74
     possible
    1.72
    mere
    1.70
    Activations Density 0.230%

    No Known Activations