© 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. 7035
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a popular science fiction franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to "Star Trek" characters and elements from the franchise

    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
     Flavoring
    -0.78
     tremend
    -0.75
    arettes
    -0.73
    ffield
    -0.72
    iquid
    -0.71
    urgical
    -0.69
    anmar
    -0.68
    ailability
    -0.68
    urgy
    -0.68
    iamond
    -0.67
    POSITIVE LOGITS
    lace
    0.77
    USS
    0.73
    patrick
    0.72
     Yards
    0.68
    ble
    0.68
    brace
    0.68
    hoff
    0.68
     hump
    0.66
    kies
    0.65
    Crew
    0.64
    Activations Density 0.112%

    No Known Activations