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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 19727
    Prev
    Next
    INDEX
    Explanations

    mentions of bowls

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eanor
    -0.65
    nesota
    -0.60
     Anarchy
    -0.59
    Domin
    -0.59
    akin
    -0.59
    selves
    -0.58
     arresting
    -0.58
     Anton
    -0.57
    apse
    -0.57
     Agency
    -0.57
    POSITIVE LOGITS
     bowl
    1.15
    bowl
    1.12
     bowls
    0.98
    hend
    0.93
    pipe
    0.93
    cup
    0.89
     Bowl
    0.88
    halla
    0.79
    stein
    0.76
    Å¡
    0.75
    Activations Density 0.007%

    No Known Activations