© 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. 24763
    Prev
    Next
    INDEX
    Explanations

    references to specific technologies or programming 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/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
    369
    +0.20
    1.1%
    397
    +0.19
    1.1%
    412
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.20
    0.04
    403
    +0.19
    0.04
    412
    +0.13
    0.03
    Negative Logits
    ¨
    -2.31
    ©
    -2.13
    Ķ
    -2.09
    ł
    -2.08
    ¼
    -2.08
    ĩ
    -2.01
    »¿
    -1.99
    µ
    -1.96
    ¢
    -1.95
    ĸ´
    -1.93
    POSITIVE LOGITS
    rosse
    1.85
    affe
    1.84
    nut
    1.72
    hetto
    1.62
    ulf
    1.60
    reate
    1.54
    reek
    1.54
    aussian
    1.51
    RPC
    1.49
    iosity
    1.46
    Activations Density 0.073%

    No Known Activations