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. 2896
    Prev
    Next
    INDEX
    Explanations

    mentions of fires, firefighters, and related events

    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
    1013
    +0.11
    0.3%
    576
    +0.10
    0.3%
    939
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.11
    0.04
    736
    +0.10
    0.05
    166
    +0.10
    0.03
    Negative Logits
     :)))
    -0.81
     interro
    -0.81
     applau
    -0.77
     sonor
    -0.71
     ciment
    -0.71
     fondamental
    -0.70
     Realt
    -0.70
     hairc
    -0.70
     pép
    -0.70
     astu
    -0.69
    POSITIVE LOGITS
     fire
    0.89
     firefighters
    0.86
     fires
    0.83
     burning
    0.83
     flames
    0.81
     firefighting
    0.77
     arson
    0.76
    fire
    0.73
     burn
    0.70
     extinguished
    0.70
    Activations Density 0.304%

    No Known Activations