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. 542
    Prev
    Next
    INDEX
    Explanations

    mentions of items or objects associated with pockets

    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
    0.9%
    1872
    +0.11
    0.7%
    687
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1872
    +0.16
    0.03
    1233
    +0.11
    0.02
    1557
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.84
    /***
    
    -0.90
    ⓧ
    -0.82
    ///**
    -0.70
    /*!
    
    -0.70
     endow
    -0.65
    żdy
    -0.65
     reinstate
    -0.64
    /**
    
    
    -0.62
     rehabilitate
    -0.61
    POSITIVE LOGITS
    Pocket
    1.38
     pocket
    1.37
     Pocket
    1.34
    pocket
    1.27
     Jambi
    1.13
     pockets
    1.12
     Pockets
    1.09
     thuy
    1.07
     maroc
    1.03
     jawa
    1.03
    Activations Density 0.071%

    No Known Activations