© 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. 20081
    Prev
    Next
    INDEX
    Explanations

    words related to gasoline and fuel

    oai_token-act-pair · gpt-3.5-turbo

    mentions of gasoline and petrol-related terms

    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
    atar
    -0.73
    Ç
    -0.73
    Guard
    -0.73
    Cro
    -0.69
     Upload
    -0.67
    Unique
    -0.65
     Cro
    -0.64
     Subjects
    -0.64
    perfect
    -0.62
    umb
    -0.61
    POSITIVE LOGITS
     gasoline
    3.64
     petrol
    3.09
     diesel
    1.90
     fuel
    1.83
     petroleum
    1.82
     gas
    1.80
    Gas
    1.64
    gas
    1.63
     ethanol
    1.50
     Diesel
    1.46
    Activations Density 0.017%

    No Known Activations