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. 15519
    Prev
    Next
    INDEX
    Explanations

    references to physical bowls or container objects commonly associated with storing or serving food

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bowls

    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
     Lauder
    -0.84
    kson
    -0.74
    eanor
    -0.69
    bourg
    -0.69
    apse
    -0.68
     Jenner
    -0.66
     Monarch
    -0.64
     Bundes
    -0.64
     Phantom
    -0.64
     Hugo
    -0.64
    POSITIVE LOGITS
    pipe
    1.09
    cup
    0.96
    bowl
    0.95
    ers
    0.94
     bowl
    0.90
    hend
    0.86
    pour
    0.85
    ful
    0.81
    gary
    0.81
     bowls
    0.80
    Activations Density 0.036%

    No Known Activations