© 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. 0-RES-JB
    11. 14984
    Prev
    Next
    INDEX
    Explanations

    phrases related to public speaking

    oai_token-act-pair · gpt-3.5-turbo

    mentions of speeches

    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
    mount
    -0.66
    Factor
    -0.66
    oy
    -0.65
    OR
    -0.64
    onica
    -0.64
     Tier
    -0.64
     contamin
    -0.64
    fecture
    -0.63
    uel
    -0.62
    isf
    -0.61
    POSITIVE LOGITS
     speeches
    3.78
     lectures
    1.94
     speech
    1.89
     presentations
    1.74
    speech
    1.71
     Speech
    1.63
     rallies
    1.62
     briefings
    1.61
     seminars
    1.54
     slogans
    1.47
    Activations Density 0.018%

    No Known Activations