© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 10622
    Prev
    Next
    INDEX
    Explanations

    terms related to specificity and targeted processes

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    156
    +0.18
    1.0%
    327
    +0.12
    0.7%
    339
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.18
    0.02
    326
    +0.12
    0.02
    18
    +0.11
    0.03
    Negative Logits
    uler
    -1.84
    Bankr
    -1.63
    rated
    -1.63
    osecond
    -1.59
    rein
    -1.56
    rade
    -1.54
    IRD
    -1.54
    mozilla
    -1.49
    uvre
    -1.47
    "}](#
    -1.46
    POSITIVE LOGITS
    £
    4.01
    Ń
    3.93
    ¨
    3.83
    ¥
    3.77
    ©
    3.75
    Ĭ
    3.75
    Īĺ
    3.73
    Ł
    3.64
    ĸ
    3.63
    ĵ
    3.61
    Activations Density 0.125%

    No Known Activations