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. 14644
    Prev
    Next
    INDEX
    Explanations

    information related to educational and professional background of individuals, focusing on degrees, affiliations, and career details

    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
    +0.20
    0.8%
    1741
    +0.10
    0.4%
    227
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.20
    0.08
    490
    +0.10
    0.06
    1870
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.05
    ⓧ
    -1.00
    /**
    -0.93
    
    
    -0.89
    <?
    -0.84
    /*++
    -0.74
    /*
    -0.72
    <?
    
    -0.70
     springfox
    -0.60
     tighten
    -0.59
    POSITIVE LOGITS
     saar
    1.37
     Græ
    1.37
     bandung
    1.33
     kasa
    1.28
     lele
    1.28
     kafe
    1.27
     kaos
    1.27
     Minang
    1.26
     Præ
    1.22
     karton
    1.21
    Activations Density 0.521%

    No Known Activations