© 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. 8-RES-JB
    11. 9940
    Prev
    Next
    INDEX
    Explanations

    references to the Mandelbrot set

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific set or collection named "Mandelbrot."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.74
    ï¸
    -0.72
     Typhoon
    -0.72
     Spit
    -0.70
     sights
    -0.65
    spection
    -0.64
    stocks
    -0.63
     FT
    -0.63
    FFFF
    -0.63
    CLOSE
    -0.62
    POSITIVE LOGITS
    olin
    1.23
    arin
    1.10
    erer
    1.05
    ela
    1.02
    eer
    1.01
    atory
    1.00
    rag
    1.00
    ered
    1.00
    arine
    1.00
    rake
    0.96
    Activations Density 0.039%

    No Known Activations