© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20836
    Prev
    Next
    INDEX
    Explanations

    words related to trailers or promotional material for films or shows

    oai_token-act-pair · gpt-3.5-turbo

    references to trailers or previews of films and games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Admin
    -0.82
    ¬¼
    -0.79
     mathemat
    -0.72
    urrency
    -0.67
     subsistence
    -0.65
    ente
    -0.65
    nesota
    -0.64
    orem
    -0.64
    verning
    -0.64
    edIn
    -0.64
    POSITIVE LOGITS
     trailer
    1.39
     trailers
    1.22
     teaser
    1.21
     tease
    1.12
     Trailer
    1.05
     showcasing
    1.00
     footage
    0.99
     screenshots
    0.98
     teased
    0.97
     IMAGES
    0.95
    Activations Density 0.133%

    No Known Activations