© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12277
    Prev
    Next
    INDEX
    Explanations

    references to judges and court-related terms

    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
    451
    +0.10
    0.6%
    71
    +0.10
    0.6%
    21
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.10
    0.02
    177
    +0.10
    0.02
    451
    +0.10
    0.01
    Negative Logits
     footing
    -1.51
     affected
    -1.49
    amethasone
    -1.45
     neighbouring
    -1.44
    own
    -1.43
     cleaner
    -1.37
     neighbours
    -1.34
     match
    -1.32
    ed
    -1.32
     licence
    -1.31
    POSITIVE LOGITS
    NEY
    1.70
    μÎŃ
    1.61
    ãĤĥ
    1.56
    Argued
    1.55
    ********************************
    1.50
    .:
    1.49
    doms
    1.49
    .,
    1.45
    οÏħÏĤ
    1.45
    æģ¯
    1.44
    Activations Density 0.081%

    No Known Activations