© 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. 7-RES-JB
    11. 24053
    Prev
    Next
    INDEX
    Explanations

    instances of actions or events occurring in a public setting

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being in public or public settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onite
    -0.80
    nian
    -0.78
    ptoms
    -0.78
    ostic
    -0.77
    zzy
    -0.77
    umar
    -0.77
    auga
    -0.76
    vana
    -0.74
    xit
    -0.72
    hner
    -0.68
    POSITIVE LOGITS
     venues
    1.04
     arenas
    1.04
     restrooms
    0.94
     places
    0.93
     spaces
    0.89
     toilets
    0.87
     parks
    0.86
     booths
    0.85
     gatherings
    0.83
     lobb
    0.83
    Activations Density 0.052%

    No Known Activations