© 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. 0-RES-JB
    11. 1973
    Prev
    Next
    INDEX
    Explanations

    mentions of the color "white" with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "white" and its context in describing various subjects or themes

    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
     mort
    -0.70
     Bern
    -0.65
     fort
    -0.64
     Arche
    -0.64
     overload
    -0.63
     agon
    -0.61
     arc
    -0.61
     dive
    -0.60
     bite
    -0.60
     ail
    -0.60
    POSITIVE LOGITS
    white
    3.89
    White
    2.35
    black
    2.07
     WHITE
    1.87
     white
    1.81
    brown
    1.73
    yellow
    1.68
     White
    1.53
    gray
    1.53
     whites
    1.52
    Activations Density 0.019%

    No Known Activations