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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3469
    Prev
    Next
    INDEX
    Explanations

    information related to fuel prices and gasoline rationing

    oai_token-act-pair · gpt-3.5-turbo

    references to fuel prices and fuel-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shant
    -1.02
     Dharma
    -0.97
     Wong
    -0.94
    Tai
    -0.89
     Vaj
    -0.87
    Pokémon
    -0.87
     ninja
    -0.82
    atana
    -0.81
     Skull
    -0.81
    Chan
    -0.81
    POSITIVE LOGITS
    Gas
    2.02
     gasoline
    1.99
     Gas
    1.90
     gas
    1.87
    gas
    1.78
     fuel
    1.73
     Fuel
    1.66
     diesel
    1.63
    Fuel
    1.59
     ethanol
    1.58
    Activations Density 0.240%

    No Known Activations