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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 14862
    Prev
    Next
    INDEX
    Explanations

    phrases related to muscle health and anatomy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1942
    +0.13
    0.7%
    50
    +0.12
    0.6%
    1331
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1331
    +0.13
    0.03
    1942
    +0.12
    0.03
    74
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.79
     intersper
    -0.97
     endow
    -0.88
     underval
    -0.85
     defray
    -0.80
     gratify
    -0.79
     incarcer
    -0.78
     endeavored
    -0.77
     strove
    -0.76
     appraise
    -0.76
    POSITIVE LOGITS
     muscle
    1.35
     Muscle
    1.29
     muscles
    1.25
    muscle
    1.23
    Muscle
    1.20
     riva
    1.01
     Muscles
    1.00
    Mus
    0.97
     MUS
    0.97
     saar
    0.94
    Activations Density 0.130%

    No Known Activations