© 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. 10-RES_POST_32K-OAI
    11. 27395
    Prev
    Next
    INDEX
    Explanations

    questions that inquire about possibilities, outcomes, and assessments

    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
    18
    +0.13
    0.6%
    218
    +0.12
    0.5%
    57
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    60
    +0.13
    0.07
    348
    +0.12
    0.05
    218
    +0.11
    0.04
    Negative Logits
    GV
    -0.69
     shouldn
    -0.66
    important
    -0.65
     rightfully
    -0.65
     KNOW
    -0.65
     cautioned
    -0.64
    AFTA
    -0.63
    should
    -0.62
    essential
    -0.62
    identified
    -0.62
    POSITIVE LOGITS
     unfolds
    0.73
     develops
    0.69
     happens
    0.69
    hare
    0.67
     unfold
    0.65
     fate
    0.64
     fruition
    0.63
     others
    0.63
     reaction
    0.63
     Carbuncle
    0.62
    Activations Density 0.363%

    No Known Activations