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. 0-RES-JB
    6. 23951
    Prev
    Next
    INDEX
    Explanations

    references to various types of literature in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to literature and its significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hatch
    -0.71
    estone
    -0.70
     Boss
    -0.68
     Tune
    -0.66
    match
    -0.64
    gged
    -0.64
     Shutdown
    -0.63
     Rounds
    -0.62
    Factor
    -0.61
    Boss
    -0.61
    POSITIVE LOGITS
     literature
    3.92
     Literature
    2.68
     folklore
    1.47
     writings
    1.47
     books
    1.35
     publications
    1.33
     textbooks
    1.33
     poetry
    1.33
     literary
    1.30
     novels
    1.29
    Activations Density 0.017%

    No Known Activations