© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 30402
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, particularly angle brackets and operators associated with template structures and generic programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.14
    0.7%
    692
    +0.10
    0.5%
    158
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.14
    0.04
    158
    +0.10
    0.04
    701
    +0.10
    0.03
    Negative Logits
     cuff
    -0.73
    leans
    -0.72
    ovember
    -0.70
     defic
    -0.69
    rogens
    -0.65
     spons
    -0.64
    upon
    -0.64
     nodd
    -0.64
     laun
    -0.63
     amnesty
    -0.62
    POSITIVE LOGITS
    >(
    1.14
    _>
    0.99
    char
    0.92
     unsigned
    0.87
     bool
    0.86
     int
    0.84
     Integer
    0.84
    uint
    0.83
    String
    0.82
    >
    0.81
    Activations Density 0.102%

    No Known Activations