© 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. 1-RES-SM
    11. 24182
    Prev
    Next
    INDEX
    Explanations

    C++ code structure and syntax elements

    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/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
    401
    +0.16
    0.9%
    5
    +0.11
    0.6%
    466
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.16
    0.03
    419
    +0.11
    0.03
    101
    +0.10
    0.03
    Negative Logits
    IJ
    -2.75
    ¦
    -2.68
    Ī
    -2.67
    Ĭ
    -2.63
    ½
    -2.57
    Į
    -2.52
    »
    -2.51
    Ĩ
    -2.49
    ¹
    -2.48
    ĩ
    -2.40
    POSITIVE LOGITS
    documentclass
    1.46
    mith
    1.43
     tire
    1.43
    atorial
    1.42
     conformation
    1.40
     repeat
    1.38
    scientific
    1.36
     sciences
    1.36
    cout
    1.35
    pherd
    1.34
    Activations Density 0.265%

    No Known Activations