© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26473
    Prev
    Next
    INDEX
    Explanations

    numeric values or identifiers related to dates or statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    166
    +0.10
    0.4%
    380
    +0.09
    0.4%
    750
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.01
    755
    +0.09
    0.01
    609
    +0.09
    0.02
    Negative Logits
     Cue
    -0.70
     Provided
    -0.63
     Older
    -0.61
     Gin
    -0.60
    ometimes
    -0.60
     Turtles
    -0.60
     LF
    -0.60
     Hide
    -0.59
     delegation
    -0.57
     Toro
    -0.56
    POSITIVE LOGITS
    ³
    0.94
    اØ
    0.87
    ãĤ¢ãĥ«
    0.87
    ª
    0.85
    ا
    0.83
    ãĤ¯
    0.82
    ãĤ¹
    0.79
    ¹
    0.79
    Ñĥ
    0.78
    ¸
    0.77
    Activations Density 0.111%

    No Known Activations