© 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. 8-RES_POST_32K-OAI
    11. 4154
    Prev
    Next
    INDEX
    Explanations

    elements related to statistical or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    756
    +0.13
    0.6%
    226
    +0.12
    0.5%
    87
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.13
    0.22
    615
    +0.12
    0.15
    143
    +0.09
    0.15
    Negative Logits
     needles
    -0.68
     nodd
    -0.64
    hedon
    -0.64
    icing
    -0.61
    oru
    -0.60
     crunch
    -0.60
    ondon
    -0.60
    magic
    -0.60
    roup
    -0.60
    stuff
    -0.60
    POSITIVE LOGITS
     Conclusion
    0.94
     Lastly
    0.83
     Summary
    0.78
     Further
    0.78
    Furthermore
    0.76
     Regarding
    0.76
    Conclusion
    0.76
     Accordingly
    0.75
    Figure
    0.75
    Additionally
    0.73
    Activations Density 0.700%

    No Known Activations