© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4883
    Prev
    Next
    INDEX
    Explanations

    references to web development and programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    16
    +0.12
    0.5%
    649
    +0.11
    0.5%
    269
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.02
    659
    +0.11
    0.02
    343
    +0.10
    0.02
    Negative Logits
    Reviewer
    -0.88
    æĺ¯
    -0.85
    lasses
    -0.79
    ãĥ´
    -0.79
    ships
    -0.77
    é¾
    -0.75
    rum
    -0.75
     Nanto
    -0.74
    riel
    -0.72
    é¾įå¥ij士
    -0.70
    POSITIVE LOGITS
     artisan
    0.83
    enty
    0.79
    ombie
    0.74
    abre
    0.73
    unit
    0.72
    urious
    0.72
    afort
    0.72
    ombies
    0.71
    atham
    0.69
    isodes
    0.69
    Activations Density 0.072%

    No Known Activations