© 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. 29099
    Prev
    Next
    INDEX
    Explanations

    file paths and configurations related to system operations

    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
    637
    +0.12
    0.5%
    504
    +0.10
    0.4%
    530
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.03
    345
    +0.10
    0.03
    505
    +0.09
    0.02
    Negative Logits
    ItemThumbnailImage
    -0.63
     Samar
    -0.62
    tery
    -0.62
    acci
    -0.62
     Malf
    -0.61
     Rohing
    -0.61
    elson
    -0.60
     misunderstanding
    -0.59
     incorrectly
    -0.59
    ework
    -0.59
    POSITIVE LOGITS
    /.
    0.97
    \/
    0.85
    bin
    0.81
    ãĤ¨ãĥ«
    0.80
    /,
    0.77
     Documents
    0.74
    ãĥ¼ãĤ¯
    0.73
     âĶľâĶĢâĶĢ
    0.72
    actionDate
    0.71
    \\\\
    0.70
    Activations Density 0.209%

    No Known Activations