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. 8-RES-JB
    6. 6691
    Prev
    Next
    INDEX
    Explanations

    text related to physical objects with specific features, such as colors, shapes, and materials

    oai_token-act-pair · gpt-3.5-turbo

    descriptive elements related to color and texture in objects

    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
     Markets
    -0.78
    Daily
    -0.71
    deals
    -0.71
    Commerce
    -0.68
    agame
    -0.68
    Financial
    -0.68
    arcity
    -0.68
    storm
    -0.67
    Politics
    -0.66
    Services
    -0.66
    POSITIVE LOGITS
     protr
    1.37
     nipple
    1.06
     diagonal
    0.98
     seam
    0.97
     clasp
    0.95
     elong
    0.95
     zipper
    0.95
     markings
    0.94
     seams
    0.92
     insertion
    0.91
    Activations Density 0.918%

    No Known Activations