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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 3773
    Prev
    Next
    INDEX
    Explanations

    references to science

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "science" in various contexts

    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
     STATES
    -0.66
    oser
    -0.63
    terior
    -0.62
    raine
    -0.62
    ESH
    -0.61
    leased
    -0.61
     Hearts
    -0.61
    âĢ¢âĢ¢
    -0.60
     Seasons
    -0.60
     Kessler
    -0.60
    POSITIVE LOGITS
     fiction
    1.25
     Fiction
    1.21
    icist
    0.98
    fiction
    0.95
    craft
    0.91
     literacy
    0.87
    istries
    0.80
    mong
    0.80
    sonian
    0.79
    bench
    0.77
    Activations Density 0.049%

    No Known Activations