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. 6-RES-JB
    6. 22269
    Prev
    Next
    INDEX
    Explanations

    colors or color-related objects

    oai_token-act-pair · gpt-3.5-turbo

    colors and their shades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Players
    -0.92
    =-=-=-=-
    -0.88
    rers
    -0.87
    Reloaded
    -0.83
    arenthood
    -0.81
    Attempts
    -0.78
    ========
    -0.78
    ãĥĦ
    -0.77
    ocard
    -0.75
     mathemat
    -0.75
    POSITIVE LOGITS
     tint
    1.06
     eyed
    1.04
     coloured
    1.04
     colored
    1.02
     oval
    0.98
     hue
    0.97
     silhouette
    0.96
     ribbon
    0.96
     metallic
    0.95
     rectangular
    0.92
    Activations Density 0.147%

    No Known Activations