© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15377
    Prev
    Next
    INDEX
    Explanations

    mentions of and references to bowls

    oai_token-act-pair · gpt-3.5-turbo

    references to bowls, particularly in cooking or serving contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.74
    kson
    -0.72
    apse
    -0.67
    bourg
    -0.65
     Benson
    -0.65
     Assass
    -0.61
     Bundes
    -0.61
     Draper
    -0.60
     Jenner
    -0.60
     Monarch
    -0.60
    POSITIVE LOGITS
    pipe
    1.04
    bowl
    0.97
    ers
    0.95
    cup
    0.92
     bowl
    0.90
     bowls
    0.85
    pour
    0.84
    waters
    0.83
    ful
    0.82
    tie
    0.81
    Activations Density 0.039%

    No Known Activations