© 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. 8-RES-JB
    11. 10503
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and data processing

    oai_token-act-pair · gpt-3.5-turbo

    structured data or code-related concepts associated with campaigns and widgets

    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
     scrut
    -0.70
    ecause
    -0.68
    ournal
    -0.66
     Aires
    -0.65
    natureconservancy
    -0.65
     Yel
    -0.62
    eas
    -0.62
    erella
    -0.61
    icably
    -0.60
    sed
    -0.60
    POSITIVE LOGITS
    _
    1.37
    __
    1.20
    _-_
    1.16
    ___
    0.93
    _.
    0.90
    ()
    0.86
    _(
    0.85
    ():
    0.77
    llor
    0.75
    ())
    0.74
    Activations Density 0.101%

    No Known Activations