© 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. 1-RES-JB
    11. 20006
    Prev
    Next
    INDEX
    Explanations

    references to clowns and related characters in a humorous or satirical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to clowns

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WARD
    -0.67
    Britain
    -0.64
    ces
    -0.62
    WI
    -0.62
    ced
    -0.61
    RA
    -0.60
    AAF
    -0.59
    ecd
    -0.58
    cing
    -0.58
    CE
    -0.58
    POSITIVE LOGITS
     Clown
    1.16
     clown
    0.96
    fish
    0.86
    ortium
    0.80
    opard
    0.80
    obyl
    0.74
    cats
    0.74
     Luffy
    0.74
     Chaser
    0.72
    ey
    0.72
    Activations Density 0.010%

    No Known Activations