© 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. 14428
    Prev
    Next
    INDEX
    Explanations

    coordinates and parameters within mathematical functions and equations

    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
    397
    +0.17
    1.0%
    17
    +0.13
    0.7%
    78
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.17
    0.04
    448
    +0.13
    0.05
    17
    +0.12
    0.03
    Negative Logits
     whom
    -1.63
     actors
    -1.54
    fare
    -1.52
    bies
    -1.51
     members
    -1.50
     ability
    -1.48
     methods
    -1.46
    ungen
    -1.45
    asks
    -1.43
     approval
    -1.40
    POSITIVE LOGITS
    cex
    1.98
    ^*,
    1.74
    ^
    1.68
    UV
    1.57
    ^*
    1.53
    Axis
    1.52
    mapsto
    1.52
    YY
    1.51
    ^{(
    1.50
    ^{[
    1.49
    Activations Density 0.198%

    No Known Activations