© 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. 28938
    Prev
    Next
    INDEX
    Explanations

    numerical scores related to anxiety and depression 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
    145
    +0.14
    0.6%
    6
    +0.11
    0.5%
    369
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.14
    0.08
    6
    +0.11
    0.09
    145
    +0.10
    0.08
    Negative Logits
    udeb
    -0.93
    ModLoader
    -0.88
    orously
    -0.83
    conservancy
    -0.79
    undreds
    -0.79
     volunte
    -0.79
     neighb
    -0.77
    oku
    -0.76
    liga
    -0.75
    rats
    -0.74
    POSITIVE LOGITS
     Ratio
    1.11
     Measures
    1.02
     Relative
    1.01
     Conclusion
    1.01
     Estimated
    0.99
     Racial
    0.99
     Adjusted
    0.99
     Weight
    0.98
     Percentage
    0.97
     Median
    0.97
    Activations Density 0.495%

    No Known Activations