© 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. 11-RES-JB
    11. 7590
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sci-fi and fantasy franchises, especially focusing on characters, locations, and titles within those franchises

    oai_token-act-pair · gpt-3.5-turbo

    references to comic book or superhero franchises

    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
     isEnabled
    -0.63
    currently
    -0.62
     awaits
    -0.62
    continue
    -0.62
    omorphic
    -0.60
    includes
    -0.58
     shall
    -0.58
     avail
    -0.56
    rounded
    -0.55
     await
    -0.53
    POSITIVE LOGITS
     earlier
    0.92
     when
    0.90
    ixties
    0.88
     last
    0.87
     years
    0.85
     onwards
    0.82
     shortly
    0.79
    !.
    0.78
     ago
    0.78
    .[
    0.78
    Activations Density 0.495%

    No Known Activations