© 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. 8-RES_POST_32K-OAI
    11. 8361
    Prev
    Next
    INDEX
    Explanations

    references to prominent organizations, individuals, and social issues

    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
    186
    +0.12
    0.5%
    762
    +0.11
    0.5%
    376
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.17
    186
    +0.11
    0.11
    401
    +0.09
    0.13
    Negative Logits
    FTWARE
    -0.70
    »Ĵ
    -0.70
     Additional
    -0.69
     detailing
    -0.69
    near
    -0.67
    fitted
    -0.67
     accompanying
    -0.66
     concluding
    -0.64
    Additional
    -0.63
    Detailed
    -0.63
    POSITIVE LOGITS
     ain
    1.51
     sucks
    1.50
     hates
    1.29
     shouldn
    1.23
     ALWAYS
    1.16
     gotta
    1.15
     isn
    1.14
     doesnt
    1.12
     doesn
    1.09
     loves
    1.06
    Activations Density 2.997%

    No Known Activations