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. 0-RES-JB
    6. 17358
    Prev
    Next
    INDEX
    Explanations

    names or terms related to individuals named "burn"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "burn" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nar
    -0.64
     gener
    -0.62
     Haitian
    -0.61
     fraternity
    -0.61
     plural
    -0.61
    essage
    -0.61
     Kas
    -0.60
     Kik
    -0.60
    »Ĵ
    -0.59
     Pr
    -0.59
    POSITIVE LOGITS
    burn
    4.71
    burning
    2.06
    Burn
    2.04
     Burn
    1.67
     burner
    1.60
     burn
    1.57
     burns
    1.47
    bourne
    1.47
    bur
    1.22
     burned
    1.18
    Activations Density 0.012%

    No Known Activations