© 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. 28236
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data or statistics

    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
    71
    +0.10
    0.5%
    754
    +0.10
    0.5%
    314
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.10
    0.02
    430
    +0.10
    0.02
    241
    +0.10
    0.02
    Negative Logits
    anyl
    -0.80
     unden
    -0.76
    inarily
    -0.72
     perspect
    -0.67
    staking
    -0.67
     enthusi
    -0.64
     trave
    -0.63
     enthus
    -0.63
     lapt
    -0.62
     paran
    -0.62
    POSITIVE LOGITS
    1
    0.89
     1
    0.84
    DIV
    0.82
    709
    0.81
     216
    0.80
     226
    0.79
     246
    0.78
     146
    0.77
     147
    0.76
    601
    0.76
    Activations Density 0.072%

    No Known Activations