© 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. 9-RES-JB
    11. 20800
    Prev
    Next
    INDEX
    Explanations

    mentions of personal interests and career trajectory involving art, music, and technology

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal interests and creativity

    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
     delegates
    -0.81
     Pelosi
    -0.77
     senators
    -0.75
    ulus
    -0.74
     witnesses
    -0.73
     Yad
    -0.73
     plaintiffs
    -0.73
     Plaint
    -0.71
    vind
    -0.70
     disputed
    -0.70
    POSITIVE LOGITS
     hobbies
    1.58
     hobby
    1.36
    Favorite
    1.14
     passions
    1.11
     passion
    1.04
    Growing
    1.01
     pursuits
    1.00
    obbies
    0.98
     fascination
    0.98
     blogging
    0.94
    Activations Density 0.891%

    No Known Activations