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. 3058
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and exercise

    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
    1437
    +0.11
    0.4%
    1515
    +0.10
    0.3%
    1865
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1437
    +0.11
    0.03
    1351
    +0.10
    0.02
    74
    +0.10
    0.02
    Negative Logits
     accla
    -1.10
     emphat
    -1.00
     maneu
    -0.99
     cushi
    -0.95
     shenan
    -0.94
     volunte
    -0.94
     reluct
    -0.94
     ugg
    -0.90
     strick
    -0.88
     encomp
    -0.87
    POSITIVE LOGITS
     gym
    1.18
     fitness
    1.13
     workout
    0.98
     Fitness
    0.97
    fitness
    0.94
     gyms
    0.94
     Gym
    0.90
    Fitness
    0.89
    gym
    0.86
     FITNESS
    0.85
    Activations Density 0.178%

    No Known Activations