© 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. 8971
    Prev
    Next
    INDEX
    Explanations

    copyright-related terms and references

    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
    +0.11
    0.5%
    350
    +0.10
    0.4%
    492
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.03
    615
    +0.10
    0.02
    301
    +0.09
    0.01
    Negative Logits
    hered
    -0.76
    bol
    -0.72
    notes
    -0.72
    anos
    -0.68
    visors
    -0.67
    conserv
    -0.66
    ilt
    -0.65
    vich
    -0.64
    Corp
    -0.62
    uild
    -0.62
    POSITIVE LOGITS
    TERN
    0.69
     unused
    0.66
    cept
    0.64
    CVE
    0.61
     Aad
    0.61
    ¨
    0.60
    nexpected
    0.57
     appetite
    0.57
     Geoffrey
    0.56
    Keith
    0.56
    Activations Density 0.041%

    No Known Activations