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. 2378
    Prev
    Next
    INDEX
    Explanations

    details related to wedding invitations and events

    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
    •fun features

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.27
    1.0%
    1013
    +0.09
    0.3%
    1244
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    798
    +0.27
    0.06
    469
    +0.09
    0.05
    181
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.11
    ⓧ
    -0.99
    <?
    -0.86
    /**
    -0.86
    
    
    -0.79
    /*
    -0.71
     EconPapers
    -0.67
    żdy
    -0.65
    /***
    
    -0.64
    <?
    
    -0.64
    POSITIVE LOGITS
     maneu
    1.47
     accla
    1.42
     impra
    1.33
     reluct
    1.33
     wherea
    1.32
     uniqu
    1.30
     strick
    1.29
     increa
    1.28
     Intere
    1.27
     lele
    1.26
    Activations Density 0.955%

    No Known Activations