© 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 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. 30701
    Prev
    Next
    INDEX
    Explanations

    key phrases related to significant events or milestones

    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
    373
    +0.19
    0.9%
    481
    +0.15
    0.7%
    442
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    539
    +0.19
    0.29
    640
    +0.15
    0.28
    143
    +0.09
    0.28
    Negative Logits
     Caption
    -0.62
    auri
    -0.58
     Applicant
    -0.58
    furt
    -0.55
    onym
    -0.55
     Ezek
    -0.54
    doms
    -0.54
     Ong
    -0.53
     seiz
    -0.53
     Feedback
    -0.53
    POSITIVE LOGITS
    Advertisements
    0.86
    UMP
    0.73
    Spoiler
    0.70
    )=
    0.70
    :(
    0.70
    :-
    0.69
    THE
    0.68
    OIL
    0.68
    =
    0.67
    TH
    0.67
    Activations Density 1.659%

    No Known Activations