© 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. 31232
    Prev
    Next
    INDEX
    Explanations

    references to online community discussions or questions about specific topics

    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
    613
    +0.11
    0.5%
    250
    +0.10
    0.4%
    187
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.01
    477
    +0.10
    0.03
    293
    +0.10
    0.03
    Negative Logits
     Greenwich
    -0.70
     Gron
    -0.68
     RN
    -0.67
     Vera
    -0.67
     Melania
    -0.67
     supermarkets
    -0.66
    ĸļ
    -0.65
     Lauder
    -0.65
    aughs
    -0.65
    ograp
    -0.64
    POSITIVE LOGITS
    topic
    1.28
    thread
    1.25
    Thread
    1.19
    forum
    1.04
     thread
    1.00
    msg
    0.95
     topic
    0.94
     forum
    0.94
     Thread
    0.93
    forums
    0.93
    Activations Density 0.362%

    No Known Activations