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. 8419
    Prev
    Next
    INDEX
    Explanations

    information regarding plane incidents and airport facilities

    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
    939
    +0.15
    0.4%
    1120
    +0.13
    0.4%
    1499
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.15
    0.06
    1499
    +0.13
    0.05
    203
    +0.13
    0.04
    Negative Logits
     😭😭
    -0.70
     emphat
    -0.67
     ?...
    -0.66
     :)))
    -0.63
     🥲
    -0.62
     🤣🤣
    -0.62
     !...
    -0.62
     cytoplas
    -0.61
     sven
    -0.60
     catast
    -0.60
    POSITIVE LOGITS
     airport
    0.80
     Airport
    0.73
     facilities
    0.71
     facility
    0.70
     airports
    0.66
    Airport
    0.63
    Facilities
    0.62
     runway
    0.59
     Facilities
    0.56
     airfield
    0.56
    Activations Density 0.308%

    No Known Activations