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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-JB
    6. 10116
    Prev
    Next
    INDEX
    Explanations

    mentions of clowns

    oai_token-act-pair · gpt-3.5-turbo

    references to clowns and their various representations in a comedic or satirical context

    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
    WARD
    -0.72
    ecd
    -0.70
    ction
    -0.69
    ãĥ´
    -0.66
    RA
    -0.65
    selection
    -0.65
    ULTS
    -0.65
    cing
    -0.65
    AAF
    -0.65
    ASED
    -0.65
    POSITIVE LOGITS
     clown
    1.05
     Clown
    1.02
    fish
    0.94
     mascot
    0.80
    opard
    0.75
    obyl
    0.72
    ovy
    0.72
    oon
    0.71
     shark
    0.71
    s
    0.71
    Activations Density 0.009%

    No Known Activations