© 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. 26335
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics related to sports performance

    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
    314
    +0.14
    0.7%
    217
    +0.10
    0.5%
    572
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    689
    +0.14
    0.07
    220
    +0.10
    0.08
    260
    +0.10
    0.08
    Negative Logits
     Attribution
    -0.81
    76561
    -0.74
     Mé
    -0.69
    Reply
    -0.67
     '.
    -0.67
    isation
    -0.66
     Bakr
    -0.64
     «
    -0.64
    igm
    -0.63
     honoured
    -0.62
    POSITIVE LOGITS
    ft
    0.95
    pc
    0.89
    placed
    0.80
    m
    0.76
    illin
    0.74
    cms
    0.73
    gel
    0.73
    mc
    0.73
    league
    0.72
    pm
    0.72
    Activations Density 0.802%

    No Known Activations