© 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. 28841
    Prev
    Next
    INDEX
    Explanations

    URLs or web links

    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
    218
    +0.13
    0.6%
    314
    +0.13
    0.6%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.13
    0.01
    284
    +0.13
    0.02
    160
    +0.11
    0.02
    Negative Logits
     interpol
    -0.76
     ERA
    -0.72
     Buddh
    -0.72
     Ans
    -0.71
     que
    -0.70
     pse
    -0.70
     Tac
    -0.69
     Relief
    -0.69
     IQ
    -0.69
     citations
    -0.68
    POSITIVE LOGITS
    www
    1.85
    twitter
    1.61
    facebook
    1.37
    goo
    1.36
    youtu
    1.33
    steam
    1.29
    localhost
    1.25
    imgur
    1.24
    bleacher
    1.23
    redd
    1.22
    Activations Density 0.085%

    No Known Activations