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. 6176
    Prev
    Next
    INDEX
    Explanations

    instances of a service or product being provided or offered

    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
    +0.23
    1.4%
    1271
    +0.11
    0.7%
    1909
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    849
    +0.23
    0.06
    1271
    +0.11
    0.06
    1993
    +0.09
    0.06
    Negative Logits
    <bos>
    -3.22
    ⓧ
    -0.96
    
    
    -0.79
    <?
    -0.70
    /**
    -0.65
    GEBURTSDATUM
    -0.62
    Література
    -0.58
    /***
    
    -0.57
    #![
    -0.56
     disbur
    -0.55
    POSITIVE LOGITS
     bandung
    1.12
     thuy
    1.10
     aquarelle
    1.10
     chèvre
    1.09
     provence
    1.09
     lele
    1.08
     pép
    1.07
     cannes
    1.04
     ananas
    1.04
     maroc
    1.03
    Activations Density 0.313%

    No Known Activations