© 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. 14058
    Prev
    Next
    INDEX
    Explanations

    occurrences of code-related inclusion directives

    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
    21
    +0.26
    1.6%
    9
    +0.14
    0.9%
    78
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.26
    0.03
    312
    +0.14
    0.04
    9
    +0.14
    0.03
    Negative Logits
    aru
    -1.37
    htra
    -1.36
    ?’
    -1.33
    thood
    -1.31
     favorably
    -1.28
    ?",
    -1.26
    arers
    -1.26
    soever
    -1.25
    ?'
    -1.24
    ableness
    -1.24
    POSITIVE LOGITS
    include
    2.77
    ĭ
    2.70
    ²
    2.63
    ¼
    2.62
    ij
    2.56
    ģ
    2.55
    Ĭ
    2.54
    IJ
    2.44
    ½
    2.36
    °
    2.35
    Activations Density 0.089%

    No Known Activations