© 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. 27028
    Prev
    Next
    INDEX
    Explanations

    instances of referencing documents, studies, or sections throughout the text

    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
    196
    +0.13
    0.6%
    756
    +0.11
    0.5%
    760
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.13
    0.08
    540
    +0.11
    0.11
    317
    +0.11
    0.09
    Negative Logits
     shenan
    -0.71
     prank
    -0.71
    ?!"
    -0.68
     moms
    -0.62
     crap
    -0.61
    Joined
    -0.60
     Ness
    -0.60
     poop
    -0.59
    Made
    -0.57
     dads
    -0.56
    POSITIVE LOGITS
     below
    1.31
     hereafter
    1.24
     briefly
    1.19
     herein
    1.17
     extensively
    1.13
     separately
    1.11
    below
    1.05
     elsewhere
    1.04
     comprehens
    1.02
     here
    1.00
    Activations Density 1.603%

    No Known Activations