Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 10207
    Prev
    Next
    INDEX
    Explanations

    references to the science fiction franchise Star Trek

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Star Trek" franchise and its various series and movies

    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
    ividual
    -0.95
    displayText
    -0.74
    inventoryQuantity
    -0.73
    iard
    -0.71
    hap
    -0.70
     reconc
    -0.69
    essage
    -0.69
    ebin
    -0.68
    untled
    -0.68
    aunder
    -0.65
    POSITIVE LOGITS
    kies
    1.12
     Expedition
    0.96
     Voyager
    0.90
    kie
    0.87
    Movie
    0.87
     Beyond
    0.85
     Nemesis
    0.84
     Cruiser
    0.84
     Generations
    0.84
     Enterprise
    0.83
    Activations Density 0.023%

    No Known Activations