© 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. 4927
    Prev
    Next
    INDEX
    Explanations

    food-related terms, food-related activities, and names of food establishments

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

    instances of the word "craze" and its variations

    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
    manship
    -0.61
     Democrats
    -0.60
     theorem
    -0.58
     Maher
    -0.58
    ions
    -0.58
    iments
    -0.57
     Tracks
    -0.57
     Robin
    -0.57
     Down
    -0.56
     Democrat
    -0.56
    POSITIVE LOGITS
    igslist
    1.53
    ze
    1.43
    fters
    1.40
    fter
    1.27
    pload
    1.26
    ven
    1.07
    ved
    1.03
    ves
    1.01
    ving
    0.97
    pton
    0.92
    Activations Density 0.027%

    No Known Activations