© 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. 30034
    Prev
    Next
    INDEX
    Explanations

    the presence of specific peptides related to psychological conditions

    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
    702
    +0.11
    0.5%
    448
    +0.11
    0.5%
    586
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.01
    711
    +0.11
    0.02
    659
    +0.10
    0.04
    Negative Logits
    phia
    -0.72
    pora
    -0.69
    owan
    -0.69
    Bey
    -0.68
    gow
    -0.67
    pent
    -0.67
    akuya
    -0.66
    worthy
    -0.65
    crop
    -0.64
    swick
    -0.63
    POSITIVE LOGITS
    itaire
    0.91
    ãĥİ
    0.73
    ids
    0.73
    itte
    0.70
    ID
    0.69
    id
    0.66
    it
    0.65
    ido
    0.64
    IT
    0.64
    line
    0.64
    Activations Density 0.792%

    No Known Activations