© 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. 13932
    Prev
    Next
    INDEX
    Explanations

    explicit statistical or programming parameters related to data structures and code snippets

    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
    29
    +0.15
    0.8%
    277
    +0.12
    0.6%
    212
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.15
    0.09
    78
    +0.12
    0.00
    27
    +0.11
    0.11
    Negative Logits
    ”).
    -2.69
    ”.
    -2.34
    .”
    -2.20
    ”)
    -2.19
    .”).
    -2.11
    ”;
    -1.93
    $).
    -1.90
    âĢ¦”
    -1.82
    ?”
    -1.80
    ”),
    -1.79
    POSITIVE LOGITS
    §
    5.32
    IJ
    5.29
    Ķ
    5.18
    ķ
    5.14
    ¸
    5.06
    ľĵ
    5.01
    ŀ
    4.98
    ¨
    4.98
    Ĩ
    4.97
    ¡
    4.97
    Activations Density 1.882%

    No Known Activations