© 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. 25493
    Prev
    Next
    INDEX
    Explanations

    keys and key identifiers in code or data structures

    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
    269
    +0.11
    0.6%
    504
    +0.11
    0.6%
    379
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.11
    0.03
    351
    +0.11
    0.03
    504
    +0.10
    0.03
    Negative Logits
    IJ
    -3.05
    Ĥ
    -3.02
    ·¸
    -2.83
    ·
    -2.80
    ↵Č
    -2.80
    ↵
    -2.80
    -2.80
    ↵↵
    -2.80
    ↵
    -2.80
    ↵
    -2.80
    POSITIVE LOGITS
    tees
    2.01
    rooms
    1.95
    buk
    1.92
    boards
    1.89
    ahead
    1.78
    aho
    1.76
    arters
    1.75
    makers
    1.74
    quarters
    1.73
    pad
    1.73
    Activations Density 0.068%

    No Known Activations