© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 15709
    Prev
    Next
    INDEX
    Explanations

    specific mentions of colors within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to color and color-related concepts

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

    No Comments

    Negative Logits
    doms
    -1.08
    _-
    -0.93
    idem
    -0.92
    iddles
    -0.77
    olicy
    -0.75
    uckland
    -0.74
    yu
    -0.72
    Xi
    -0.71
    minster
    -0.71
    rican
    -0.70
    POSITIVE LOGITS
     palette
    1.11
    blind
    1.02
     color
    1.01
     colors
    0.99
    color
    0.96
     colours
    0.92
     tint
    0.91
     colour
    0.87
    grain
    0.86
     dye
    0.86
    Activations Density 0.018%

    No Known Activations