© 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. 26643
    Prev
    Next
    INDEX
    Explanations

    statements of analysis or conclusions about 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
    760
    +0.13
    0.6%
    130
    +0.11
    0.5%
    381
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.13
    0.10
    70
    +0.11
    0.12
    688
    +0.11
    0.10
    Negative Logits
    gee
    -0.60
    ËĪ
    -0.59
     [&
    -0.56
    zona
    -0.56
    Initialized
    -0.55
    ãĥİ
    -0.53
     [+
    -0.53
     Reincarnated
    -0.52
    pmwiki
    -0.52
    Fake
    -0.51
    POSITIVE LOGITS
     therefore
    1.81
     however
    1.74
     moreover
    1.70
     furthermore
    1.68
     meanwhile
    1.66
     then
    1.37
     though
    1.27
     also
    1.25
     accordingly
    1.23
     thus
    1.20
    Activations Density 2.010%

    No Known Activations