© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9039
    Prev
    Next
    INDEX
    Explanations

    the word "with" used in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    308
    +0.10
    0.4%
    462
    +0.09
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.06
    608
    +0.09
    0.06
    60
    +0.09
    0.04
    Negative Logits
    nown
    -0.81
    within
    -0.70
    Allows
    -0.68
    ware
    -0.68
     nowhere
    -0.68
    cffff
    -0.68
    humane
    -0.68
     eternity
    -0.67
    arde
    -0.66
    something
    -0.66
    POSITIVE LOGITS
     Orchestra
    0.90
    rew
    0.70
    Guest
    0.70
     slideshow
    0.67
     introduction
    0.64
     exception
    0.64
     honorary
    0.63
     Juliet
    0.63
     Edited
    0.63
    ©¶æ
    0.62
    Activations Density 0.463%

    No Known Activations