© 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. 2-RES-SM
    11. 31859
    Prev
    Next
    INDEX
    Explanations

    references to specific categories or sections within a document

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    59
    +0.15
    0.9%
    46
    +0.14
    0.8%
    487
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.15
    0.02
    46
    +0.14
    0.02
    487
    +0.12
    0.02
    Negative Logits
    OUP
    -1.70
    idyl
    -1.63
    izumab
    -1.57
    ucleotide
    -1.55
    zech
    -1.54
    Unit
    -1.46
     homolog
    -1.45
    ipes
    -1.44
     derivatives
    -1.42
    amycin
    -1.36
    POSITIVE LOGITS
    stood
    2.34
    neath
    2.19
    lining
    2.04
    lying
    2.04
    standing
    1.97
    stand
    1.97
    wear
    1.86
    cover
    1.83
    lined
    1.81
    lies
    1.75
    Activations Density 0.056%

    No Known Activations