© 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. 26400
    Prev
    Next
    INDEX
    Explanations

    references to data structures or objects in programming contexts

    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
    167
    +0.13
    0.6%
    31
    +0.12
    0.5%
    515
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.13
    0.02
    255
    +0.12
    0.02
    679
    +0.10
    0.02
    Negative Logits
    DAY
    -0.83
    ornia
    -0.76
    forth
    -0.73
    HER
    -0.73
    coni
    -0.70
    bred
    -0.68
    creen
    -0.67
    warts
    -0.64
    ndra
    -0.64
     Deity
    -0.64
    POSITIVE LOGITS
    ives
    1.01
    ivist
    0.96
    ivity
    0.96
    ively
    0.93
    ive
    0.92
     oriented
    0.86
    ÑĮ
    0.85
    ivism
    0.82
    ified
    0.81
    ification
    0.78
    Activations Density 0.110%

    No Known Activations