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. 1010
    Prev
    Next
    INDEX
    Explanations

    phrases related to surrounding oneself or others, particularly in a context of influence or environment

    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
    +0.24
    1.3%
    2004
    +0.12
    0.7%
    1222
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2004
    +0.24
    0.03
    1222
    +0.12
    0.02
    1491
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.65
    /***
    
    -0.73
    ///**
    -0.69
    func
    -0.68
    ⓧ
    -0.68
    frac
    -0.64
     earn
    -0.64
    <>
    
    -0.63
    fetch
    -0.61
    Пра
    -0.60
    POSITIVE LOGITS
     lele
    1.78
     fta
    1.74
     ftu
    1.74
     thut
    1.71
     aen
    1.65
     fup
    1.63
     »>
    1.55
     fua
    1.53
     tew
    1.51
     ftre
    1.50
    Activations Density 0.058%

    No Known Activations