© 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. 0-RES-JB
    11. 6839
    Prev
    Next
    INDEX
    Explanations

    references to clowns and Joker in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to clowns and related characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AU
    -0.76
     Aus
    -0.71
    bi
    -0.70
     Qi
    -0.69
    ét
    -0.69
     Allen
    -0.69
    abit
    -0.68
    Allen
    -0.67
    ulf
    -0.67
    Recommend
    -0.67
    POSITIVE LOGITS
     clown
    3.60
     Clown
    3.48
     Joker
    1.55
     Bard
    1.32
     circus
    1.19
     Laugh
    1.17
     pupp
    1.15
     maniac
    1.11
     Jugg
    1.11
    iddler
    1.10
    Activations Density 0.029%

    No Known Activations