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. 5422
    Prev
    Next
    INDEX
    Explanations

    phrases related to inviting people to visit or join a place or event

    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
    +0.25
    1.0%
    1013
    +0.10
    0.4%
    755
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.25
    0.08
    755
    +0.10
    0.07
    1013
    +0.09
    0.09
    Negative Logits
    <bos>
    -2.41
    /*
    -0.78
     enable
    -0.74
    /**
    -0.71
    ⓧ
    -0.70
    #
    -0.66
     enables
    -0.66
     serve
    -0.65
    //
    -0.64
     activate
    -0.64
    POSITIVE LOGITS
     emphat
    1.68
     maneu
    1.67
     Juf
    1.66
     accla
    1.65
     unden
    1.63
     affor
    1.60
     reluct
    1.60
     desir
    1.60
     fta
    1.57
     impra
    1.57
    Activations Density 0.830%

    No Known Activations