© 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. 29216
    Prev
    Next
    INDEX
    Explanations

    references to America and its people

    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
    111
    +0.17
    1.0%
    71
    +0.15
    0.9%
    241
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.17
    -0.00
    241
    +0.15
    0.01
    71
    +0.15
    0.02
    Negative Logits
    ting
    -1.88
    outs
    -1.65
    such
    -1.64
     otherwise
    -1.63
    dling
    -1.61
     themselves
    -1.60
    dle
    -1.55
     outs
    -1.53
     enough
    -1.52
     ourselves
    -1.52
    POSITIVE LOGITS
    ½
    2.23
    ¡
    2.23
    ī
    2.17
    Ľ
    2.16
    ł
    2.13
    ŀ
    2.05
    ĭ
    2.02
    »¿
    2.00
    Ĩ
    1.92
    ĩ
    1.92
    Activations Density 0.074%

    No Known Activations