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. 738
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions and processes

    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
    50
    +0.17
    0.9%
    506
    +0.11
    0.6%
    281
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1451
    +0.17
    0.03
    281
    +0.11
    0.03
    966
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.61
    /***
    
    -0.76
    
    
    -0.72
    ⓧ
    -0.66
     resourceCulture
    -0.65
    contentLoaded
    -0.65
    elemField
    -0.60
     mit
    -0.60
     виправи
    -0.60
     близь
    -0.59
    POSITIVE LOGITS
     affor
    1.72
     maneu
    1.71
     milano
    1.71
     frankfurt
    1.66
     stockholm
    1.64
     napoli
    1.57
     reluct
    1.56
     maroc
    1.54
     lidl
    1.54
     bandung
    1.52
    Activations Density 0.064%

    No Known Activations