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. 0-RES-JB
    6. 57
    Prev
    Next
    INDEX
    Explanations

    mentions of military service, veterans, and related organizations and benefits

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.07
    0.3%
    327
    +0.07
    0.3%
    405
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    327
    +0.07
    0.04
    147
    +0.07
    0.03
    78
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.11
    ⓧ
    -0.77
    /*++
    -0.76
    }{||
    -0.73
    /**
    -0.72
    /*
    -0.65
    <?
    -0.64
    hline
    -0.63
    ,
    -0.63
    void
    -0.62
    POSITIVE LOGITS
    Veterans
    1.95
     Veterans
    1.91
     Veter
    1.91
     Veteran
    1.88
     veterans
    1.88
     Juf
    1.71
     Khart
    1.70
    Veteran
    1.69
     impra
    1.67
     emphat
    1.66
    Activations Density 0.133%

    No Known Activations