© 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. 6-RES-JB
    11. 11990
    Prev
    Next
    INDEX
    Explanations

    references to space-related terms and characters from a specific science fiction franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Enterprise" and associated characters from the "Star Trek" franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anmar
    -0.87
     tremend
    -0.84
    anguage
    -0.84
    urgical
    -0.83
    udic
    -0.83
    iquid
    -0.81
    iqu
    -0.81
    aukee
    -0.80
    ideshow
    -0.80
    hesis
    -0.78
    POSITIVE LOGITS
     Yards
    0.99
     NX
    0.78
    Crew
    0.77
     Voyager
    0.77
    lace
    0.76
     Enterprise
    0.75
     Crew
    0.74
     Trek
    0.73
     Klingon
    0.70
     Nationwide
    0.69
    Activations Density 0.064%

    No Known Activations