© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 18138
    Prev
    Next
    INDEX
    Explanations

    words relating to the act of burning

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "burned" or its variations

    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
    ont
    -0.77
     Greenberg
    -0.73
    clusive
    -0.72
    berman
    -0.69
     Zealand
    -0.68
    FN
    -0.67
    voc
    -0.65
    artisan
    -0.64
    ouver
    -0.64
    ent
    -0.63
    POSITIVE LOGITS
     burned
    3.71
     burnt
    3.02
     burn
    2.37
     burns
    2.37
     burning
    2.23
     charred
    2.02
    burning
    1.87
    Burn
    1.67
     destroyed
    1.57
     Burn
    1.57
    Activations Density 0.018%

    No Known Activations