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. 5387
    Prev
    Next
    INDEX
    Explanations

    references to the word "partial"

    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
    +0.16
    0.7%
    1265
    +0.10
    0.4%
    1480
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.16
    0.04
    395
    +0.10
    0.03
    1594
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.31
    ⓧ
    -0.81
    <?
    
    -0.81
    
    
    -0.76
    /***
    
    -0.65
    ///**
    -0.59
    <?
    -0.56
    /*!
    
    -0.56
    /**
    -0.56
     maintain
    -0.53
    POSITIVE LOGITS
     Partial
    1.04
     stockholm
    1.02
    Partial
    1.00
     Partially
    0.99
     partial
    0.98
     umo
    0.98
     santiago
    0.98
     prétend
    0.97
     tanga
    0.95
     ftre
    0.95
    Activations Density 0.229%

    No Known Activations