© 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. 8-RES-JB
    11. 13126
    Prev
    Next
    INDEX
    Explanations

    mentions of the number of people that can fit or participate in different scenarios or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the capacity and accommodation of spaces or groups

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Rebell
    -0.99
    ģĸ
    -0.80
    codes
    -0.77
     Ending
    -0.76
     discoveries
    -0.74
    Quote
    -0.74
     prophe
    -0.74
     Recipes
    -0.74
     Diseases
    -0.73
    chieve
    -0.73
    POSITIVE LOGITS
     indoors
    1.28
     spectators
    1.11
     seating
    1.07
     spectator
    1.03
     nearby
    1.00
     cla
    0.98
     screened
    0.97
     outdoors
    0.95
     seated
    0.95
     strapped
    0.94
    Activations Density 0.989%

    No Known Activations