© 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. 4117
    Prev
    Next
    INDEX
    Explanations

    the word "flame" and related terms in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to fire or flames

    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
    alian
    -0.90
    llah
    -0.80
    omo
    -0.73
    oral
    -0.72
     Geographic
    -0.70
    ortment
    -0.68
    pai
    -0.68
    lus
    -0.68
    ographics
    -0.67
    Lean
    -0.67
    POSITIVE LOGITS
     flame
    1.07
     hotter
    1.01
    flies
    1.00
     extinguished
    1.00
     flames
    0.99
     retard
    0.98
     furnace
    0.93
     ignited
    0.91
     flickering
    0.90
     ashes
    0.90
    Activations Density 0.067%

    No Known Activations