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 · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8369
    Prev
    Next
    INDEX
    Explanations

    references related to fuel and fuel-related activities such as fueling, subsidies, and different types of fuels

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1839
    +0.12
    0.4%
    67
    +0.12
    0.4%
    528
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1464
    +0.12
    0.02
    67
    +0.12
    0.02
    1507
    +0.11
    0.02
    Negative Logits
     racon
    -0.76
     fortn
    -0.72
     benevol
    -0.68
     evoc
    -0.67
     intrigu
    -0.66
     philosophic
    -0.65
     Machia
    -0.65
     pamph
    -0.65
     accla
    -0.64
     dismant
    -0.63
    POSITIVE LOGITS
     fuel
    1.44
    fuel
    1.34
     Fuel
    1.28
    Fuel
    1.27
     fuels
    1.25
     FUEL
    1.18
    fuels
    1.00
    FUEL
    0.99
     Fuels
    0.97
     fueled
    0.85
    Activations Density 0.071%

    No Known Activations