© 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. 5523
    Prev
    Next
    INDEX
    Explanations

    specific locations or events mentioned in the text

    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
    294
    +0.10
    0.5%
    244
    +0.09
    0.4%
    65
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.10
    0.05
    380
    +0.09
    0.04
    115
    +0.09
    0.06
    Negative Logits
    natureconservancy
    -0.76
    rez
    -0.74
    catentry
    -0.70
    sem
    -0.70
    ullivan
    -0.70
    xon
    -0.68
    isy
    -0.67
    thood
    -0.67
    anges
    -0.66
    frames
    -0.64
    POSITIVE LOGITS
     Calif
    1.28
     Ont
    1.11
     California
    1.09
     Fla
    1.09
     Ontario
    1.09
     Illinois
    1.08
     Colo
    1.07
     Texas
    1.00
     Ohio
    0.99
     CA
    0.96
    Activations Density 0.447%

    No Known Activations