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. 724
    Prev
    Next
    INDEX
    Explanations

    the concept of gravity and its discussions in various contexts

    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
    871
    +0.18
    0.9%
    50
    +0.16
    0.8%
    442
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    871
    +0.18
    0.02
    442
    +0.16
    0.02
    370
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.03
    ⓧ
    -0.66
    <>
    
    -0.66
    
    
    -0.66
    <?
    
    -0.63
    /***
    
    -0.61
    Библи
    -0.56
     regenerate
    -0.56
    żdy
    -0.54
     innovate
    -0.53
    POSITIVE LOGITS
     gravity
    1.48
     Gravity
    1.42
    gravity
    1.27
    Gravity
    1.26
     GRAV
    1.09
     gravitational
    0.96
     chèvre
    0.95
    setGravity
    0.90
     Karang
    0.89
    vitational
    0.86
    Activations Density 0.080%

    No Known Activations