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. 6-RES-JB
    6. 5302
    Prev
    Next
    INDEX
    Explanations

    text related to correspondence and communication

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    331
    +0.14
    0.6%
    50
    +0.11
    0.5%
    1387
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.03
    814
    +0.11
    0.02
    1387
    +0.11
    0.02
    Negative Logits
    <bos>
    -1.93
    
    
    -0.76
    Въ
    -0.67
    #
    -0.67
    ganu
    -0.61
     bu
    -0.60
    elemField
    -0.60
    ઊ
    -0.60
    util
    -0.59
    exitRule
    -0.59
    POSITIVE LOGITS
     bandung
    1.69
     aen
    1.57
     jacques
    1.56
     lele
    1.55
     jaya
    1.50
     emphat
    1.49
     lara
    1.49
     ricardo
    1.48
     fei
    1.46
     haup
    1.46
    Activations Density 0.165%

    No Known Activations