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. 528
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal growth and self-improvement

    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
    +0.15
    0.6%
    1705
    +0.09
    0.4%
    2016
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.15
    0.11
    2016
    +0.09
    0.06
    1314
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.86
    /***
    
    -0.61
     fulfill
    -0.60
    //---
    -0.59
    &
    -0.58
     rely
    -0.58
    //...
    -0.58
     establish
    -0.58
    //@
    -0.57
     employ
    -0.57
    POSITIVE LOGITS
     bandung
    1.44
     soggior
    1.42
     bayern
    1.34
     bordeaux
    1.30
     napoli
    1.30
     swarovski
    1.29
     palio
    1.28
     maroc
    1.28
     nutella
    1.25
     paradiso
    1.25
    Activations Density 1.572%

    No Known Activations