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. 14841
    Prev
    Next
    INDEX
    Explanations

    sentences related to personal experiences, activities, and emotions

    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
    0.9%
    381
    +0.13
    0.6%
    1013
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.20
    0.17
    381
    +0.13
    0.01
    1013
    +0.12
    0.19
    Negative Logits
    <bos>
    -2.87
    ⓧ
    -0.83
    /**
    -0.71
    },{
    
    -0.70
    /***
    
    -0.66
    /**
    
    
    -0.65
    <?
    
    -0.63
     establish
    -0.63
    /*
    -0.61
     deliver
    -0.60
    POSITIVE LOGITS
     unwarran
    1.45
     myn
    1.45
     disagre
    1.44
     reluct
    1.43
     tolerably
    1.43
     impra
    1.41
     increa
    1.41
     lele
    1.35
     unce
    1.35
     gaily
    1.34
    Activations Density 5.387%

    No Known Activations