Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20341
    Prev
    Next
    INDEX
    Explanations

    mentions of gasoline-related terms and topics

    oai_token-act-pair · gpt-3.5-turbo

    references to gasoline prices and related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arat
    -0.81
     Proud
    -0.75
    èª
    -0.74
    lihood
    -0.71
    osen
    -0.70
     CLSID
    -0.69
    "]=>
    -0.69
    achu
    -0.68
    iverse
    -0.67
    ivas
    -0.67
    POSITIVE LOGITS
     gasoline
    1.25
     fuel
    0.95
    oline
    0.93
     fumes
    0.90
     excise
    0.86
     petrol
    0.86
     gas
    0.84
     fueling
    0.82
     mileage
    0.82
     diesel
    0.82
    Activations Density 0.009%

    No Known Activations