© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    6. 20338
    Prev
    Next
    INDEX
    Explanations

    words related to shades or colors

    oai_token-act-pair · gpt-3.5-turbo

    references to color or variations in light and shade

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.82
    ICLE
    -0.78
    ulate
    -0.77
    ilia
    -0.73
    ciating
    -0.72
    ties
    -0.72
    ERN
    -0.70
    glomer
    -0.70
    ilus
    -0.70
    entric
    -0.69
    POSITIVE LOGITS
     tint
    1.02
     shades
    0.97
     shade
    0.94
     Flavoring
    0.90
     curtains
    0.88
    creen
    0.86
     Shade
    0.85
    skinned
    0.82
     shading
    0.82
     Shades
    0.80
    Activations Density 0.071%

    No Known Activations