© 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. 2289
    Prev
    Next
    INDEX
    Explanations

    references to movies, actors, and specific roles within the film industry

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

    names of actors and their roles in films

    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
     mathemat
    -0.96
    £ı
    -0.95
    BIP
    -0.80
    devices
    -0.77
     territ
    -0.73
    wcs
    -0.71
    endars
    -0.70
     disag
    -0.68
    papers
    -0.68
    âĸ¬
    -0.68
    POSITIVE LOGITS
     actor
    1.50
     actors
    1.38
     actresses
    1.35
    actor
    1.29
     actress
    1.28
     Bale
    1.27
     Actor
    1.25
    Actor
    1.22
     Leonardo
    1.21
     Sheen
    1.17
    Activations Density 0.485%

    No Known Activations