© 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. 29531
    Prev
    Next
    INDEX
    Explanations

    instructions related to the actions or requirements for completing a task or process

    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
    23
    +0.23
    1.3%
    1
    +0.12
    0.7%
    126
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.23
    0.08
    126
    +0.12
    0.04
    478
    +0.12
    0.01
    Negative Logits
    ĩ
    -2.14
    ¾
    -2.03
    Ł
    -1.84
    ¨
    -1.80
    ¢
    -1.78
    Ń
    -1.69
    etter
    -1.68
    à±ģ
    -1.68
    apine
    -1.63
    »¿
    -1.62
    POSITIVE LOGITS
    orate
    1.56
    or
    1.56
    arer
    1.48
    orin
    1.47
    question
    1.46
     rightly
    1.42
    oarthritis
    1.41
     jeopardy
    1.39
    oe
    1.38
     asked
    1.38
    Activations Density 0.917%

    No Known Activations