© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29612
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "case" and its variations, highlighting legal or situational contexts

    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
    392
    +0.14
    0.6%
    530
    +0.10
    0.4%
    467
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.14
    0.02
    435
    +0.10
    0.02
    439
    +0.09
    0.02
    Negative Logits
    natureconservancy
    -0.68
     haste
    -0.68
    esis
    -0.67
    SPONSORED
    -0.66
    shire
    -0.66
    uyomi
    -0.64
    lihood
    -0.63
     rites
    -0.60
     indefinite
    -0.58
    tackle
    -0.58
    POSITIVE LOGITS
    lain
    0.88
    back
    0.77
    boards
    0.75
    backs
    0.75
    ividual
    0.73
    board
    0.73
    senal
    0.73
    idon
    0.72
    agher
    0.72
    fat
    0.70
    Activations Density 0.169%

    No Known Activations