© 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. 28260
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement, calculation, and assessment

    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
    +0.12
    0.6%
    262
    +0.10
    0.4%
    67
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.14
    255
    +0.10
    0.12
    439
    +0.08
    0.08
    Negative Logits
     Revelations
    -0.72
     Inquisition
    -0.70
    reon
    -0.69
     Shutterstock
    -0.69
    elected
    -0.65
    gallery
    -0.64
    nces
    -0.63
     reckoning
    -0.63
    dding
    -0.61
     WRITE
    -0.61
    POSITIVE LOGITS
    worthiness
    1.15
     strengths
    0.95
     weaknesses
    0.95
     hazards
    0.94
     optimal
    0.93
     optimum
    0.90
     merits
    0.90
     thresholds
    0.90
     risks
    0.86
     potential
    0.84
    Activations Density 2.355%

    No Known Activations