© 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. 30558
    Prev
    Next
    INDEX
    Explanations

    sequences of events or repetitions within the text

    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
    497
    +0.10
    0.5%
    469
    +0.10
    0.5%
    490
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.10
    0.03
    651
    +0.10
    0.03
    387
    +0.10
    0.03
    Negative Logits
    Drag
    -0.65
    azer
    -0.61
    VICE
    -0.60
    icka
    -0.60
    dogs
    -0.60
    WAR
    -0.59
    ibur
    -0.59
     Wrestling
    -0.58
     Mormonism
    -0.58
    Favorite
    -0.57
    POSITIVE LOGITS
     succession
    0.80
     series
    0.72
     spate
    0.71
    series
    0.71
     barrage
    0.69
     flurry
    0.66
     number
    0.65
    Ĥª
    0.63
    ãĤ¦ãĤ¹
    0.61
     handful
    0.59
    Activations Density 0.201%

    No Known Activations