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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 7215
    Prev
    Next
    INDEX
    Explanations

    movie genres or types of films

    oai_token-act-pair · gpt-3.5-turbo

    titles and descriptions of various film and television genres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spons
    -0.80
     credential
    -0.78
    elong
    -0.77
    ype
    -0.74
     confer
    -0.74
     podium
    -0.73
     sponsor
    -0.73
     Flickr
    -0.70
     sponsoring
    -0.70
     mailing
    -0.67
    POSITIVE LOGITS
     thriller
    1.34
     sequel
    1.20
     trilogy
    1.20
     Chronicles
    1.18
     novels
    1.17
     sequels
    1.07
     Trilogy
    1.05
     dystopian
    1.04
     Odyssey
    1.00
     dystop
    0.99
    Activations Density 1.278%

    No Known Activations