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. 11-RES-JB
    6. 4729
    Prev
    Next
    INDEX
    Explanations

    mentions of various characters, likely from a puppet show, and specific scenes or details associated with them

    oai_token-act-pair · gpt-3.5-turbo

    references to puppetry and puppet shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ept
    -0.82
    Benz
    -0.81
    ascus
    -0.80
     Sov
    -0.80
    Islamic
    -0.78
    Assad
    -0.78
    Sov
    -0.77
    hene
    -0.75
    Iraq
    -0.75
     benz
    -0.75
    POSITIVE LOGITS
     cartoons
    1.55
     cartoon
    1.54
     mascot
    1.49
     Simpsons
    1.44
     Cartoon
    1.41
     Sponge
    1.39
     Moe
    1.38
     Toad
    1.37
     masc
    1.34
     Balloon
    1.34
    Activations Density 0.576%

    No Known Activations