© 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. 31078
    Prev
    Next
    INDEX
    Explanations

    references to responses or communication regarding questions or concerns

    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
    254
    +0.10
    0.5%
    281
    +0.10
    0.4%
    452
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.10
    0.07
    235
    +0.10
    0.05
    362
    +0.09
    0.07
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.84
    toc
    -0.75
    bones
    -0.68
     Horses
    -0.68
    bilt
    -0.66
    recy
    -0.64
     Riding
    -0.63
    conserv
    -0.63
    hiba
    -0.62
    osaurus
    -0.62
    POSITIVE LOGITS
     requests
    1.58
     queries
    1.54
     inquiries
    1.45
     questions
    1.43
     complaints
    1.28
     criticisms
    1.28
     request
    1.25
     petitions
    1.25
     question
    1.22
     demands
    1.15
    Activations Density 1.245%

    No Known Activations