© 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. 1-RES-SM
    11. 25393
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and specific entities

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    369
    +0.30
    1.8%
    156
    +0.16
    0.9%
    210
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.30
    0.14
    59
    +0.16
    0.13
    410
    +0.13
    0.13
    Negative Logits
    ľĵ
    -2.23
    -1.90
    ↵
    -1.90
    -1.90
    ↵
    -1.90
    <|outofrange|>
    -1.90
    ↵
    -1.90
    ↵
    -1.90
     ↵
    -1.90
    -1.90
    POSITIVE LOGITS
    ilee
    1.85
    neys
    1.82
    bound
    1.71
    ford
    1.68
    isans
    1.66
    isan
    1.65
    IER
    1.56
     yourselves
    1.53
    aul
    1.49
     Coast
    1.49
    Activations Density 0.807%

    No Known Activations