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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 22483
    Prev
    Next
    INDEX
    Explanations

    phrases involving authors collaborating on writing or creating something, along with specific parts of documents, such as credits or acknowledgments

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that indicate collaboration or association

    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
    wings
    -0.76
     currency
    -0.67
    reality
    -0.66
    isks
    -0.64
    blocks
    -0.63
    bread
    -0.62
    bucks
    -0.62
    abus
    -0.62
    wcs
    -0.62
    tera
    -0.62
    POSITIVE LOGITS
     Patrick
    1.10
     Shawn
    1.07
     Juan
    1.07
     Samuel
    1.07
     Andrew
    1.06
     Kevin
    1.05
     Kenneth
    1.05
     Jesse
    1.04
     Buster
    1.04
     William
    1.03
    Activations Density 0.146%

    No Known Activations