© 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. 9-RES-JB
    11. 10209
    Prev
    Next
    INDEX
    Explanations

    titles of movies, games, or films

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of media, particularly titles of films and games

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     procedure
    -0.64
    uez
    -0.62
    姫
    -0.61
    ction
    -0.60
    tenance
    -0.60
    LESS
    -0.60
    ople
    -0.60
    osate
    -0.59
     Reform
    -0.59
    esville
    -0.59
    POSITIVE LOGITS
     starring
    1.00
    linger
    0.91
     featuring
    0.90
     genres
    0.86
     titles
    0.86
     marketed
    0.84
    uggest
    0.83
    manship
    0.83
    paces
    0.82
    hops
    0.81
    Activations Density 0.264%

    No Known Activations