© 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. 29396
    Prev
    Next
    INDEX
    Explanations

    content pertaining to educational topics and resources

    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
    503
    +0.16
    0.9%
    148
    +0.14
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.16
    0.03
    503
    +0.14
    0.02
    421
    +0.13
    0.01
    Negative Logits
    eper
    -1.69
     sudden
    -1.62
    eking
    -1.56
     hostile
    -1.55
    alian
    -1.51
    itsu
    -1.51
    icar
    -1.50
    eding
    -1.45
    ning
    -1.42
    idious
    -1.42
    POSITIVE LOGITS
    ĸ
    2.55
    ¿½
    2.49
    ¢
    2.48
    ķ
    2.29
    ¤
    2.29
    ĻĤ
    2.28
    ł
    2.27
    ¡
    2.26
    µ
    2.23
    ¦
    2.20
    Activations Density 0.100%

    No Known Activations