© 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. 23003
    Prev
    Next
    INDEX
    Explanations

    references to characters and events from the "Star Trek" series

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Star Trek" franchise and related elements

    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
     cig
    -0.95
    emouth
    -0.91
    iami
    -0.88
    Miami
    -0.87
     smokers
    -0.84
    ãĢ
    -0.84
     smoker
    -0.81
     Nottingham
    -0.81
    —-
    -0.80
     puff
    -0.78
    POSITIVE LOGITS
     Starfleet
    1.87
     Klingon
    1.82
     Spock
    1.61
    ajor
    1.59
     Kira
    1.58
     Voyager
    1.57
     Kling
    1.54
     Picard
    1.47
     Trek
    1.46
     Federation
    1.37
    Activations Density 0.152%

    No Known Activations