© 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. 24219
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and formatting structures related to tables and figures

    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
    31
    +0.14
    0.8%
    263
    +0.12
    0.7%
    438
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.14
    0.04
    53
    +0.12
    0.03
    309
    +0.11
    0.03
    Negative Logits
     "`
    -1.86
     term
    -1.57
     detectable
    -1.50
    »
    -1.50
     plaintiffs
    -1.45
    .\[[@
    -1.44
    `,
    -1.41
     Weinstein
    -1.39
     sequence
    -1.39
    ware
    -1.38
    POSITIVE LOGITS
    documentclass
    1.70
    aliana
    1.68
    umper
    1.60
    els
    1.55
    avel
    1.52
    STRA
    1.47
    ritis
    1.42
    oons
    1.39
    iph
    1.38
    ama
    1.36
    Activations Density 0.295%

    No Known Activations