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. 2448
    Prev
    Next
    INDEX
    Explanations

    warnings, instructions, or main points within a text

    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
    +0.18
    1.1%
    1671
    +0.13
    0.8%
    313
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.18
    0.05
    521
    +0.13
    0.06
    667
    +0.11
    0.05
    Negative Logits
    <bos>
    -3.05
    
    
    -0.95
    ⓧ
    -0.90
    /**
    -0.87
    /***
    
    -0.86
    /*
    -0.84
    /*!
    
    -0.77
    <?
    
    -0.77
    <?
    -0.75
    Kontrola
    -0.68
    POSITIVE LOGITS
     wien
    1.42
     maneu
    1.33
     impractica
    1.25
     stockholm
    1.23
     bandung
    1.21
     Czechos
    1.21
     affor
    1.21
     munich
    1.20
     impra
    1.20
     meis
    1.19
    Activations Density 0.169%

    No Known Activations