© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23803
    Prev
    Next
    INDEX
    Explanations

    items related to clothing and packing for travel

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    21
    +0.12
    0.7%
    302
    +0.11
    0.7%
    53
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.11
    21
    +0.11
    0.09
    211
    +0.10
    0.05
    Negative Logits
    quist
    -1.60
    TIF
    -1.38
    áĢ¸
    -1.37
     arsenal
    -1.34
    à¯į
    -1.32
    àµį
    -1.28
     (@
    -1.27
    áĢ¬
    -1.25
    à«ĩ
    -1.24
    PG
    -1.22
    POSITIVE LOGITS
    rap
    1.62
    pherd
    1.54
    rier
    1.47
    adays
    1.30
    ---|---
    1.29
    seeing
    1.28
    **_
    1.28
    ellation
    1.27
    že
    1.27
    ĥ½
    1.24
    Activations Density 0.831%

    No Known Activations