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. 1882
    Prev
    Next
    INDEX
    Explanations

    terms related to the passage of time and its implications or consequences

    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
    +0.21
    0.8%
    1438
    +0.09
    0.3%
    2034
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1314
    +0.21
    0.06
    1021
    +0.09
    0.07
    790
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.30
    /***
    
    -1.18
    //*/
    -1.01
     intersper
    -0.96
    Rgds
    -0.91
    Fordítás
    -0.80
    ⓧ
    -0.80
    /*!
    
    -0.80
    /*++
    -0.78
     endow
    -0.77
    POSITIVE LOGITS
    .
    0.65
     MessageType
    0.58
    cautionary
    0.56
     espectaculares
    0.56
    ;
    0.55
     OnClickListener
    0.54
     kase
    0.53
    。
    0.52
    !
    0.51
    obacz
    0.51
    Activations Density 0.635%

    No Known Activations