© 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. 25413
    Prev
    Next
    INDEX
    Explanations

    references to family and community support

    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
    +0.20
    1.1%
    379
    +0.14
    0.8%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.20
    0.05
    271
    +0.14
    0.01
    17
    +0.14
    0.03
    Negative Logits
     reservation
    -1.84
     thresholds
    -1.47
     reservations
    -1.47
     ambig
    -1.37
     counterparts
    -1.36
     pedig
    -1.35
     criteria
    -1.31
     predecessors
    -1.29
     counterpart
    -1.27
    ↵
    -1.27
    POSITIVE LOGITS
    !}
    1.57
    iger
    1.53
    !’
    1.44
    oons
    1.44
    orb
    1.41
    zig
    1.39
    veis
    1.37
    ,)
    1.37
    edly
    1.36
    food
    1.36
    Activations Density 0.259%

    No Known Activations