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. 655
    Prev
    Next
    INDEX
    Explanations

    the phrase "I'll" or its variations indicating future intent

    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
    +0.33
    1.8%
    381
    +0.13
    0.7%
    411
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.33
    0.04
    2004
    +0.13
    0.04
    1415
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.38
    </h1>
    -0.56
    HasIndex
    -0.55
    en
    -0.55
    /***
    
    -0.55
    uni
    -0.54
    public
    -0.54
     /**
    
    -0.53
    ui
    -0.53
     مرئيه
    -0.52
    POSITIVE LOGITS
     accla
    1.48
     reluct
    1.47
     maneu
    1.45
     affor
    1.41
     inev
    1.36
     shenan
    1.35
     disreg
    1.34
     disagre
    1.33
     unwarran
    1.33
     impra
    1.31
    Activations Density 0.070%

    No Known Activations