Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2970
    Prev
    Next
    INDEX
    Explanations

    color-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to color, particularly in relation to identity and societal issues

    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
     Aust
    -0.79
    NZ
    -0.77
    yip
    -0.75
    sett
    -0.71
    minist
    -0.70
    meet
    -0.70
     Gareth
    -0.70
     breached
    -0.69
     sacked
    -0.69
    loads
    -0.68
    POSITIVE LOGITS
     color
    3.66
     colors
    2.85
     colour
    2.83
    color
    2.63
     Color
    2.60
    Color
    2.56
     colored
    2.34
     coloring
    2.29
    COLOR
    2.09
    colored
    2.06
    Activations Density 0.017%

    No Known Activations