© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 23028
    Prev
    Next
    INDEX
    Explanations

    quotes or statements of different types

    oai_token-act-pair · gpt-3.5-turbo

    references to quotes and quotations

    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
    raine
    -0.69
    icultural
    -0.65
    ixture
    -0.65
    olescent
    -0.65
    icable
    -0.64
    stay
    -0.62
    ickle
    -0.59
    roller
    -0.59
    ipation
    -0.59
    endant
    -0.58
    POSITIVE LOGITS
     quotes
    4.23
     quotations
    2.96
     quote
    2.61
     quotation
    2.47
     quoted
    1.94
     quoting
    1.90
    quote
    1.64
     Quote
    1.63
    Quotes
    1.60
     excerpts
    1.50
    Activations Density 0.010%

    No Known Activations