© 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. 11759
    Prev
    Next
    INDEX
    Explanations

    mentions of being in the spotlight

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "spotlight" and related terms indicating visibility or attention

    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
    opathy
    -0.67
    gat
    -0.64
     within
    -0.63
    opot
    -0.61
     Es
    -0.60
     Conversion
    -0.60
    ==
    -0.60
    oti
    -0.60
    ental
    -0.59
     probable
    -0.59
    POSITIVE LOGITS
     spotlight
    3.93
    elight
    1.95
     Spotlight
    1.84
     microscope
    1.35
     shine
    1.26
     glare
    1.20
     highlighting
    1.17
     showcase
    1.13
     focus
    1.13
     highlight
    1.09
    Activations Density 0.007%

    No Known Activations