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. 8899
    Prev
    Next
    INDEX
    Explanations

    technical terms related to visual effects and manufacturing processes

    oai_token-act-pair · gpt-3.5-turbo

    words related to visual effects and production in filmmaking

    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
    ghazi
    -0.80
    amy
    -0.70
     Broadcasting
    -0.67
     horm
    -0.67
    usterity
    -0.67
     Welfare
    -0.66
    ega
    -0.66
     Chili
    -0.66
     Diabetes
    -0.65
    netflix
    -0.65
    POSITIVE LOGITS
    Materials
    0.99
     layouts
    0.98
     drawings
    0.95
     painter
    0.95
     sculpt
    0.95
     materials
    0.94
     sketches
    0.92
    Artist
    0.90
     layout
    0.90
     studio
    0.90
    Activations Density 0.500%

    No Known Activations