© 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. 2269
    Prev
    Next
    INDEX
    Explanations

    words related to fuel and energy sources

    oai_token-act-pair · gpt-3.5-turbo

    references to fuel and its 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
     Assassins
    -0.71
     Garfield
    -0.71
    law
    -0.69
     Alexandra
    -0.68
    anus
    -0.67
    odore
    -0.67
     Quinn
    -0.66
     Theodore
    -0.65
    pb
    -0.65
    Cro
    -0.64
    POSITIVE LOGITS
     fuel
    3.69
     Fuel
    2.68
     fuels
    2.59
    Fuel
    2.55
    fuel
    2.50
     refuel
    2.17
     gasoline
    1.93
     fueling
    1.89
     petrol
    1.68
     propell
    1.64
    Activations Density 0.025%

    No Known Activations