© 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. 9-RES-JB
    11. 15525
    Prev
    Next
    INDEX
    Explanations

    structured information such as segment titles and section headings

    oai_token-act-pair · gpt-3.5-turbo

    specific structured data or formatting markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neighb
    -0.71
     predec
    -0.68
     Vaugh
    -0.61
     administ
    -0.59
     surpr
    -0.59
     destro
    -0.59
     manif
    -0.58
     tradem
    -0.58
     Instr
    -0.58
     proble
    -0.57
    POSITIVE LOGITS
     Introduction
    0.86
    Introduction
    0.80
    [[
    0.75
     Conclusion
    0.74
    ³³³³
    0.73
    Joined
    0.71
     Quote
    0.70
    CHAPTER
    0.69
    =>
    0.68
    Offline
    0.67
    Activations Density 0.301%

    No Known Activations