© 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. 8-RES_POST_32K-OAI
    11. 9058
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the availability of detailed information and reports

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.13
    0.6%
    760
    +0.10
    0.5%
    317
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.13
    0.07
    317
    +0.10
    0.05
    306
    +0.10
    0.05
    Negative Logits
     imitation
    -0.67
     evict
    -0.64
     reclaimed
    -0.64
     commem
    -0.64
     graded
    -0.63
    akuya
    -0.63
    quit
    -0.62
     simultaneous
    -0.61
     prank
    -0.60
     perception
    -0.60
    POSITIVE LOGITS
     below
    0.92
     BELOW
    0.92
     Appendix
    0.90
     appendix
    0.88
    below
    0.85
     Below
    0.85
    available
    0.84
     Annex
    0.80
     forthcoming
    0.79
    endix
    0.79
    Activations Density 0.687%

    No Known Activations