© 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. 30872
    Prev
    Next
    INDEX
    Explanations

    box office earnings and performance statistics of films

    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
    373
    +0.12
    0.5%
    416
    +0.11
    0.5%
    207
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.11
    388
    +0.11
    0.06
    531
    +0.10
    0.06
    Negative Logits
     ,
    -0.78
     )
    -0.76
     ;
    -0.75
     Hyde
    -0.71
    Âł
    -0.71
     Gan
    -0.69
    Hy
    -0.68
     ),
    -0.67
     bricks
    -0.66
     Hindu
    -0.66
    POSITIVE LOGITS
     (+
    1.73
     (-
    1.67
     (âĪĴ
    1.35
     (/
    1.27
     ($
    1.23
     (#
    1.22
     (*
    1.18
     [+
    1.17
     (_
    1.15
     ($)
    1.12
    Activations Density 2.132%

    No Known Activations