Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6659
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time or context involving "anytime."

    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
    +0.17
    0.7%
    687
    +0.12
    0.5%
    1363
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.17
    0.06
    1994
    +0.12
    0.05
    1310
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.87
    /***
    
    -0.75
     intersper
    -0.68
     disambigu
    -0.63
    ⓧ
    -0.59
    #![
    -0.58
    },{
    
    -0.54
    ///**
    -0.53
     sec
    -0.52
    pobla
    -0.52
    POSITIVE LOGITS
     ANY
    1.00
     riva
    0.97
    ANY
    0.95
     silikon
    0.95
     grossa
    0.95
     anytime
    0.93
    ">...
    0.92
     anywhere
    0.92
     tramont
    0.92
     signora
    0.92
    Activations Density 0.220%

    No Known Activations