© 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. 29147
    Prev
    Next
    INDEX
    Explanations

    words related to legal and formal processes

    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
    156
    +0.14
    0.8%
    177
    +0.13
    0.8%
    101
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.14
    0.02
    92
    +0.13
    0.02
    177
    +0.10
    0.02
    Negative Logits
    »
    -2.64
    ĨĴ
    -2.37
    ³
    -2.34
    ·¸
    -2.33
    ©
    -2.32
    ĭ
    -2.27
    ĥ½
    -2.27
    ¹
    -2.26
    -2.25
    -2.25
    POSITIVE LOGITS
    arily
    1.95
    piece
    1.94
    vity
    1.88
    imum
    1.80
    ment
    1.71
    ments
    1.69
     mode
    1.69
    garten
    1.69
    edly
    1.64
    ÃŃf
    1.61
    Activations Density 0.146%

    No Known Activations