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. 6-RES-JB
    6. 8710
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Mandelbrot set"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Mand" and its variations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Typhoon
    -0.81
    ãģį
    -0.78
    FFFF
    -0.72
    ï¸
    -0.72
    ··
    -0.71
     Spit
    -0.70
    CLOSE
    -0.65
    terday
    -0.65
    IGH
    -0.64
    spection
    -0.63
    POSITIVE LOGITS
    olin
    1.11
    rake
    1.00
    eer
    0.99
    atory
    0.97
    arine
    0.95
    erer
    0.94
    ered
    0.93
    ingo
    0.91
    ele
    0.90
    rag
    0.89
    Activations Density 0.026%

    No Known Activations