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. 660
    Prev
    Next
    INDEX
    Explanations

    mentions of specific or definitive characteristics and details within a text

    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
    +0.21
    1.2%
    1339
    +0.14
    0.8%
    893
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1339
    +0.21
    0.04
    893
    +0.14
    0.04
    680
    +0.12
    0.03
    Negative Logits
    <bos>
    -3.43
    /***
    
    -0.84
    ///**
    -0.74
    protected
    -0.67
    public
    -0.67
    ⓧ
    -0.65
    
    
    -0.63
    //{
    
    -0.61
    /*!
    
    -0.61
     assistir
    -0.59
    POSITIVE LOGITS
     lidl
    1.30
     lele
    1.27
     milano
    1.25
     maroc
    1.24
     tramont
    1.24
     bandung
    1.23
     toledo
    1.21
     meis
    1.21
     wien
    1.21
     maneu
    1.20
    Activations Density 0.074%

    No Known Activations