© 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. 14740
    Prev
    Next
    INDEX
    Explanations

    HTML attribute assignments

    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
    21
    +0.14
    0.8%
    78
    +0.13
    0.7%
    249
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.14
    0.01
    432
    +0.13
    0.02
    325
    +0.12
    0.02
    Negative Logits
    burg
    -1.64
    ubicin
    -1.46
    omy
    -1.45
     drills
    -1.43
    houses
    -1.41
     patient
    -1.40
    hesis
    -1.37
    ienne
    -1.36
    psis
    -1.35
    teral
    -1.35
    POSITIVE LOGITS
    stylesheet
    2.73
    href
    2.29
    noop
    2.21
    author
    1.85
    oddsidemargin
    1.73
    tooltip
    1.69
    Content
    1.69
    sidebar
    1.68
    expand
    1.68
    textwidth
    1.65
    Activations Density 0.080%

    No Known Activations