© 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. 12440
    Prev
    Next
    INDEX
    Explanations

    numerical values and format specifications in a structured context

    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
    400
    +0.15
    0.8%
    277
    +0.14
    0.8%
    332
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.15
    0.06
    397
    +0.14
    0.05
    180
    +0.13
    0.05
    Negative Logits
    âĢ¢
    -1.86
     \'
    -1.81
    documentclass
    -1.50
    --"
    -1.38
     âĢ¢
    -1.35
    onial
    -1.32
     semester
    -1.29
    ""
    -1.28
     â
    -1.26
    longrightarrow
    -1.25
    POSITIVE LOGITS
     [
    5.98
    [
    5.26
    [/
    4.96
     [[
    4.47
     *[
    4.13
     [(
    4.12
     [$
    4.04
     [...]
    4.02
    [[
    3.92
     [`
    3.89
    Activations Density 1.067%

    No Known Activations