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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4784
    Prev
    Next
    INDEX
    Explanations

    colors and color-related words

    oai_token-act-pair · gpt-3.5-turbo

    colors and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Loan
    -0.81
     Inspect
    -0.77
     Administ
    -0.77
     Ticket
    -0.76
     Consent
    -0.73
    rolet
    -0.72
     Warrant
    -0.72
     Statements
    -0.71
     Fighters
    -0.71
    Coun
    -0.70
    POSITIVE LOGITS
    ish
    1.07
     hue
    0.97
     oxide
    0.96
     pigment
    0.95
     ribbon
    0.93
    ishly
    0.91
    RGB
    0.90
     coloring
    0.89
     dye
    0.89
     accents
    0.89
    Activations Density 0.084%

    No Known Activations