© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8811
    Prev
    Next
    INDEX
    Explanations

    expressions indicating direction or method

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    348
    +0.16
    0.9%
    9
    +0.14
    0.8%
    172
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.16
    0.04
    215
    +0.14
    0.03
    260
    +0.10
    0.04
    Negative Logits
    orate
    -1.50
    orian
    -1.48
    usiness
    -1.46
    iture
    -1.45
    ively
    -1.45
    ation
    -1.40
    ivity
    -1.39
     concentration
    -1.39
    rice
    -1.38
    rative
    -1.38
    POSITIVE LOGITS
    ward
    2.74
    points
    2.37
    laid
    2.08
    forward
    2.00
    fare
    1.93
    finding
    1.88
     forward
    1.87
    point
    1.85
     ahead
    1.76
    Forward
    1.68
    Activations Density 0.339%

    No Known Activations