© 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. 26319
    Prev
    Next
    INDEX
    Explanations

    expressions indicating limitations or obstacles to access and participation

    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
    756
    +0.15
    0.7%
    352
    +0.11
    0.5%
    223
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.15
    0.13
    124
    +0.11
    0.10
    718
    +0.09
    0.10
    Negative Logits
     misdem
    -0.73
    warn
    -0.72
    cens
    -0.72
    utenberg
    -0.70
    lessness
    -0.70
     FALSE
    -0.69
     disagrees
    -0.68
     misinformation
    -0.68
     inacc
    -0.68
     sqor
    -0.67
    POSITIVE LOGITS
     worthwhile
    0.95
     viable
    0.92
     productive
    0.87
     worth
    0.86
     valuable
    0.86
     cohesive
    0.85
     sustainable
    0.84
     usefulness
    0.81
     usable
    0.81
     meaningful
    0.80
    Activations Density 2.848%

    No Known Activations