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. 6863
    Prev
    Next
    INDEX
    Explanations

    instances where a subject is willing to do something or about consent

    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
    +0.26
    1.1%
    1757
    +0.12
    0.5%
    1967
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.26
    0.04
    1415
    +0.12
    0.03
    1356
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.55
    <?
    -0.90
    
    
    -0.85
    /***
    
    -0.79
    ⓧ
    -0.70
    /**
    -0.70
    ///**
    -0.66
    },{
    
    -0.57
    /*
    -0.55
    struct
    -0.54
    POSITIVE LOGITS
     bandung
    1.12
     ibiza
    1.11
     frankfurt
    1.11
     toledo
    1.11
     milano
    1.09
     santiago
    1.06
     tramont
    1.05
     barcelona
    1.04
     stockholm
    1.04
     verona
    1.01
    Activations Density 0.382%

    No Known Activations