© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29957
    Prev
    Next
    INDEX
    Explanations

    numeric data commonly associated with scores or measurements

    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
    623
    +0.11
    0.5%
    294
    +0.10
    0.5%
    350
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.11
    0.04
    430
    +0.10
    0.05
    153
    +0.10
    0.03
    Negative Logits
    encies
    -0.74
     negatives
    -0.73
    pring
    -0.72
     confir
    -0.71
     accur
    -0.70
     unnecess
    -0.70
    tons
    -0.70
    ancies
    -0.70
    typ
    -0.69
    ptions
    -0.68
    POSITIVE LOGITS
     WRITE
    0.84
     15
    0.84
     13
    0.84
     1886
    0.83
     18
    0.79
     RHP
    0.79
     14
    0.79
     19
    0.78
     16
    0.77
     22
    0.76
    Activations Density 0.234%

    No Known Activations