© 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. 26579
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and identifiers, particularly in the context of media or digital formats

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    626
    +0.10
    0.5%
    374
    +0.10
    0.5%
    132
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    626
    +0.10
    0.01
    732
    +0.10
    0.00
    373
    +0.10
    -0.02
    Negative Logits
    ibaba
    -0.76
    ividual
    -0.70
    tymology
    -0.69
    kson
    -0.69
    agara
    -0.69
    ModLoader
    -0.68
    catentry
    -0.65
    rences
    -0.65
    igree
    -0.65
    rys
    -0.65
    POSITIVE LOGITS
     Codec
    0.83
    VIDEO
    0.73
    RGB
    0.72
    CBC
    0.71
     Video
    0.71
    video
    0.71
    Movie
    0.71
    Scan
    0.70
    )=(
    0.70
    Cal
    0.70
    Activations Density 0.078%

    No Known Activations