© 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. 4-RES-SM
    11. 14452
    Prev
    Next
    INDEX
    Explanations

    command line elements and paths in programming or scripting contexts

    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
    213
    +0.15
    0.8%
    342
    +0.14
    0.8%
    293
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.15
    0.02
    370
    +0.14
    0.02
    193
    +0.12
    0.02
    Negative Logits
    pecially
    -1.89
    Ĭ
    -1.79
    least
    -1.70
     separate
    -1.51
     reviews
    -1.49
     regards
    -1.45
    pless
    -1.44
    same
    -1.44
     advantage
    -1.42
     tracts
    -1.38
    POSITIVE LOGITS
    /
    1.93
    ielder
    1.76
    der
    1.69
    /_
    1.68
    ascii
    1.65
     Laden
    1.65
    ographer
    1.63
    ograf
    1.61
    /@
    1.60
     -*-
    1.56
    Activations Density 0.117%

    No Known Activations