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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 35
    Prev
    Next
    INDEX
    Explanations

    mentions of objects or actions related to bowls

    oai_token-act-pair · gpt-3.5-turbo

    references to bowls in various contexts

    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
     Luxem
    -0.82
    DEM
    -0.75
     Mechanical
    -0.71
     Detect
    -0.69
     Koen
    -0.69
     Freem
    -0.68
     Files
    -0.66
     Agency
    -0.65
    ploy
    -0.65
     Firm
    -0.64
    POSITIVE LOGITS
     bowl
    4.04
     bowls
    3.11
    bowl
    2.57
     Bowl
    2.19
     bowling
    1.62
     basin
    1.23
     bow
    1.22
     jug
    1.22
     cup
    1.18
     skillet
    1.16
    Activations Density 0.012%

    No Known Activations