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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 12024
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Mandelbrot set."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Mandela," specifically in various contexts and usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Typhoon
    -0.74
    spect
    -0.67
    ··
    -0.67
    spection
    -0.67
    HEAD
    -0.65
    ãģį
    -0.64
    velt
    -0.61
     Spit
    -0.61
     Depth
    -0.61
    ï¸
    -0.60
    POSITIVE LOGITS
    olin
    1.22
    arin
    1.14
    ingo
    1.09
    erer
    1.04
    rag
    1.04
    ela
    1.03
    eer
    1.03
    rill
    1.03
    rake
    1.02
    atory
    1.00
    Activations Density 0.047%

    No Known Activations