© 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. 19273
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical procedures and equipment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of groups or categories of people and entities

    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
    •Few-Token Promoting Features
    Bracket Closing
    •Bracket Closing Features Layer 8 GPT2 Small

    No Comments

    Negative Logits
     guiName
    -0.90
    ãĢİ
    -0.56
    ãĢIJ
    -0.56
    etheless
    -0.54
    wcs
    -0.52
    ":[{"
    -0.50
     :=
    -0.48
     (?,
    -0.48
     [];
    -0.45
    .<
    -0.45
    POSITIVE LOGITS
    ?)
    1.80
    )
    1.79
    )."
    1.77
    !)
    1.77
    ),"
    1.74
    )"
    1.74
    )!
    1.70
    ),
    1.70
    ').
    1.69
    ')
    1.68
    Activations Density 1.557%

    No Known Activations