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. 10-RES-JB
    6. 6852
    Prev
    Next
    INDEX
    Explanations

    phrases related to sleep and rest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.22
    0.9%
    1013
    +0.11
    0.4%
    1174
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.22
    0.04
    1805
    +0.11
    0.03
    1174
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.13
     mobilize
    -0.62
     redefine
    -0.58
    public
    -0.56
    
    
    -0.52
     broaden
    -0.52
     endow
    -0.52
     rehabilitate
    -0.52
    <?
    
    -0.50
     empower
    -0.49
    POSITIVE LOGITS
     sleeping
    1.02
     peugeot
    1.00
     sleep
    0.99
     lidl
    0.97
     chrysler
    0.97
     pajero
    0.94
     pandan
    0.93
     pican
    0.92
     asleep
    0.92
     volkswagen
    0.92
    Activations Density 0.133%

    No Known Activations