© 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. 26520
    Prev
    Next
    INDEX
    Explanations

    references to competitive sports results and 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
    238
    +0.13
    0.6%
    244
    +0.13
    0.6%
    713
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.13
    274
    +0.13
    0.06
    238
    +0.10
    0.06
    Negative Logits
    bara
    -0.78
    zee
    -0.75
    achine
    -0.71
    netflix
    -0.71
    cyclopedia
    -0.67
     Anon
    -0.67
    ndra
    -0.66
    lying
    -0.65
    eller
    -0.64
    ammad
    -0.63
    POSITIVE LOGITS
     matchup
    1.15
     tie
    1.07
     showdown
    1.04
     deficit
    1.03
     shootout
    1.00
     rout
    1.00
     victory
    0.97
     clash
    0.97
     playoff
    0.96
     loss
    0.95
    Activations Density 2.098%

    No Known Activations