© 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. 13189
    Prev
    Next
    INDEX
    Explanations

    variables or data structures related to programming

    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
    402
    +0.13
    0.7%
    397
    +0.12
    0.7%
    236
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.13
    0.06
    402
    +0.12
    0.07
    371
    +0.11
    0.05
    Negative Logits
    ing
    -1.67
    ingo
    -1.65
    hood
    -1.64
    icals
    -1.60
    apine
    -1.54
    orship
    -1.53
    ers
    -1.52
    rika
    -1.51
    ontal
    -1.49
    aries
    -1.46
    POSITIVE LOGITS
    2.97
    ¨
    2.78
    Īĺ
    2.71
    IJ
    2.63
    ²
    2.48
    º
    2.42
    ·
    2.41
    ¶
    2.41
    Ī
    2.37
    Į
    2.31
    Activations Density 0.116%

    No Known Activations