© 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. 4982
    Prev
    Next
    INDEX
    Explanations

    references to the term "Boy" or "Boyz" in the text

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

    occurrences of the word "Boy"

    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
    arily
    -0.72
     gallon
    -0.61
     duplication
    -0.61
     multip
    -0.58
     surface
    -0.56
     Ful
    -0.55
    Failure
    -0.53
     pers
    -0.53
     justifying
    -0.52
    PLIC
    -0.52
    POSITIVE LOGITS
    cott
    1.60
    friend
    1.50
    cot
    1.35
    nton
    1.30
    friends
    1.28
     Scouts
    1.22
     Scout
    1.06
    ega
    1.03
    chuk
    1.02
    hood
    1.01
    Activations Density 0.020%

    No Known Activations