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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8575
    Prev
    Next
    INDEX
    Explanations

    words that express certainty, possibility, or conditions in statements

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

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    102
    +0.21
    1.1%
    55
    +0.15
    0.8%
    7
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.21
    0.14
    55
    +0.15
    0.14
    718
    +0.13
    0.11
    Negative Logits
    inav
    -0.84
    enaries
    -0.79
    atives
    -0.74
    regate
    -0.73
    ortmund
    -0.72
    doms
    -0.71
    idences
    -0.71
     Awakens
    -0.69
     Increases
    -0.68
    ieves
    -0.67
    POSITIVE LOGITS
     considered
    1.11
     supposed
    1.09
     synonymous
    1.04
     regarded
    1.04
     indistinguishable
    1.00
     irrelevant
    0.97
     indicative
    0.95
     worth
    0.95
     incompatible
    0.94
     capable
    0.93
    Activations Density 0.746%

    No Known Activations