© 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. 9002
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to various forms of structured organization and documentation

    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
    581
    +0.13
    0.6%
    495
    +0.12
    0.5%
    363
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.13
    0.05
    581
    +0.12
    0.04
    288
    +0.09
    0.06
    Negative Logits
     Relations
    -0.69
     magnets
    -0.68
    aughs
    -0.66
    bows
    -0.64
    stals
    -0.62
     Abilities
    -0.60
    Ws
    -0.60
     railways
    -0.60
    ryu
    -0.60
     Machines
    -0.58
    POSITIVE LOGITS
     imaginable
    1.53
     individually
    1.05
     conceivable
    1.02
     except
    0.93
     ounce
    0.85
    ucker
    0.78
    ologue
    0.76
    artment
    0.74
    bender
    0.73
     vying
    0.73
    Activations Density 0.351%

    No Known Activations