© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 31244
    Prev
    Next
    INDEX
    Explanations

    quantifiable statistics or data related to health and demographics

    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
    130
    +0.12
    0.5%
    750
    +0.11
    0.5%
    168
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.08
    608
    +0.11
    0.07
    616
    +0.10
    0.06
    Negative Logits
    enegger
    -0.74
    oji
    -0.69
    eele
    -0.63
    eway
    -0.58
    grounds
    -0.57
    essential
    -0.57
    zee
    -0.56
    answered
    -0.56
    unity
    -0.55
    zees
    -0.55
    POSITIVE LOGITS
     seventh
    0.84
     ninth
    0.84
     world
    0.83
     sixth
    0.82
     eighth
    0.79
     fourth
    0.77
     fifth
    0.77
     globe
    0.76
     second
    0.74
    second
    0.73
    Activations Density 0.434%

    No Known Activations