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. 43
    Prev
    Next
    INDEX
    Explanations

    technical and specialized terms related to military training or equipment

    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
    68
    +0.08
    0.3%
    50
    +0.08
    0.3%
    1810
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.06
    1120
    +0.08
    0.04
    344
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.27
    
    
    -1.17
    /**
    -0.86
    ⓧ
    -0.84
    /*
    -0.83
    <?
    -0.76
    <?
    
    -0.68
    #
    -0.63
     continue
    -0.56
    TagMode
    -0.55
    POSITIVE LOGITS
     LC
    1.11
     lele
    1.07
     Juf
    1.07
     véhic
    1.06
     fua
    1.04
     RC
    1.03
     multicolore
    1.03
     quoique
    1.01
     ftu
    1.01
     Lc
    1.01
    Activations Density 0.227%

    No Known Activations