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

    Neuronpedia

    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. 9520
    Prev
    Next
    INDEX
    Explanations

    summaries of information or text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "summary" or related terms used in various contexts

    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
     Incarn
    -0.73
    amps
    -0.71
     cared
    -0.69
    swing
    -0.68
    omet
    -0.66
     Alone
    -0.65
    amping
    -0.64
    ween
    -0.64
    kefeller
    -0.63
    areth
    -0.62
    POSITIVE LOGITS
     summary
    3.83
     Summary
    2.45
     summ
    2.32
    summary
    2.19
     synopsis
    1.96
     summar
    1.80
    Summary
    1.80
     summarize
    1.76
     overview
    1.71
     summarized
    1.58
    Activations Density 0.018%

    No Known Activations