© 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. 4-RES-SM
    11. 10160
    Prev
    Next
    INDEX
    Explanations

    questions about the feasibility or possibility of various scenarios or actions

    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
    397
    +0.15
    0.8%
    499
    +0.10
    0.6%
    505
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.15
    0.03
    15
    +0.10
    0.03
    390
    +0.10
    0.03
    Negative Logits
    Ĩ
    -4.67
    «
    -4.47
    ¼
    -4.44
    ĥ½
    -4.38
    »¿
    -4.32
    ĩ
    -4.31
    ·
    -4.30
    ĥ
    -4.29
    ·¸
    -4.26
    į
    -4.25
    POSITIVE LOGITS
     to
    2.00
     otherwise
    1.95
    bie
    1.72
    otherwise
    1.59
     using
    1.53
    opter
    1.49
     alternatively
    1.48
     else
    1.47
    psin
    1.46
    to
    1.46
    Activations Density 0.133%

    No Known Activations