© 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. 1-RES-SM
    11. 26048
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    122
    +0.10
    0.6%
    420
    +0.10
    0.6%
    347
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.10
    0.00
    1
    -0.10
    0.00
    2
    -0.10
    0.00
    Negative Logits
    cule
    -1.80
    wed
    -1.75
    ifax
    -1.72
    "}](#
    -1.56
    GREEK
    -1.54
    ľĵ
    -1.50
    emic
    -1.46
    pub
    -1.43
    unnumbered
    -1.43
    macro
    -1.42
    POSITIVE LOGITS
     objection
    1.74
    oner
    1.52
    zez
    1.47
     others
    1.39
    stant
    1.37
     scoring
    1.36
    done
    1.34
     homology
    1.33
    ayson
    1.30
     above
    1.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.