© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 2403
    Prev
    Next
    INDEX
    Explanations

    details related to sports events and activities

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    vocabulary indicating actions or events, particularly those involving movement or transmission

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    nai
    -0.73
    natureconservancy
    -0.72
    å°Ĩ
    -0.68
    nam
    -0.67
    clair
    -0.66
    artifacts
    -0.65
    galitarian
    -0.64
    Untitled
    -0.60
    keyes
    -0.59
    ãĥ¯ãĥ³
    -0.59
    POSITIVE LOGITS
     us
    1.97
     me
    1.59
     him
    1.17
     them
    1.11
     Us
    1.06
     ours
    1.02
     THEM
    0.95
     everybody
    0.86
     ourselves
    0.86
     ME
    0.83
    Activations Density 0.600%

    No Known Activations