© 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. 0-RES-JB
    11. 12306
    Prev
    Next
    INDEX
    Explanations

    expressions related to interest or attention

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing interest or curiosity about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xit
    -0.82
    Leaks
    -0.66
     smear
    -0.61
    etime
    -0.61
    yl
    -0.60
    ros
    -0.60
     slams
    -0.60
     collapses
    -0.60
    escap
    -0.59
     blasphemy
    -0.59
    POSITIVE LOGITS
     interested
    3.48
     intrigued
    1.94
     fascinated
    1.91
    interested
    1.88
     concerned
    1.79
     Interest
    1.68
     interest
    1.67
    Interested
    1.59
     willing
    1.47
     eager
    1.43
    Activations Density 0.010%

    No Known Activations