© 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 EvalsExportsinterp-engineNEWAPI 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. 24236
    Prev
    Next
    INDEX
    Explanations

    descriptions or summaries of content

    oai_token-act-pair · gpt-3.5-turbo

    structured information or summaries related to reports and assessments

    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
     helicop
    -0.70
    eur
    -0.69
    stood
    -0.64
    inse
    -0.62
    iety
    -0.62
    Je
    -0.61
    vation
    -0.59
    Daddy
    -0.59
    Wr
    -0.59
    thing
    -0.58
    POSITIVE LOGITS
     largeDownload
    0.90
     transcript
    0.78
     Transcript
    0.77
    ¶
    0.76
     Flavoring
    0.74
    recated
    0.73
     Introduction
    0.72
     ][
    0.71
     Caption
    0.69
    Ĥª
    0.68
    Activations Density 0.578%

    No Known Activations