© 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. 9042
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

    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
    500
    +0.16
    0.7%
    687
    +0.12
    0.5%
    306
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.16
    0.08
    393
    +0.12
    0.06
    385
    +0.10
    0.06
    Negative Logits
     illusion
    -0.78
     imperson
    -0.73
     delusion
    -0.69
     underdog
    -0.67
     monopoly
    -0.67
     gull
    -0.67
     organs
    -0.64
     halluc
    -0.64
     perception
    -0.63
     immortality
    -0.63
    POSITIVE LOGITS
     FAQ
    0.89
     accompanying
    0.89
     References
    0.89
     sidebar
    0.88
    ibliography
    0.88
     Contents
    0.85
     links
    0.85
     About
    0.85
     Definitions
    0.84
     attached
    0.83
    Activations Density 0.386%

    No Known Activations