© 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. 0-RES-JB
    11. 4079
    Prev
    Next
    INDEX
    Explanations

    keywords related to fossil fuels

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "fossil fuels."

    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
     Sob
    -0.73
    Channel
    -0.68
    channel
    -0.67
    dule
    -0.67
    autions
    -0.67
    rief
    -0.66
    strength
    -0.66
    Score
    -0.64
    Alert
    -0.64
     Commands
    -0.64
    POSITIVE LOGITS
     fossil
    3.79
     Foss
    2.52
     fossils
    2.48
     coal
    1.50
     dinosaur
    1.43
     geological
    1.38
     renewable
    1.34
     renewables
    1.32
     greenhouse
    1.30
     Dinosaur
    1.27
    Activations Density 0.022%

    No Known Activations