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. 907
    Prev
    Next
    INDEX
    Explanations

    references to taking time off or breaks from a routine

    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
    +0.18
    0.6%
    1013
    +0.09
    0.3%
    1233
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.18
    0.06
    1154
    +0.09
    0.04
    10
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.49
    ⓧ
    -0.70
    /*!
    
    -0.63
    <?
    -0.62
    <?
    
    -0.62
    
    
    -0.60
     establish
    -0.60
     converge
    -0.57
    ///**
    -0.57
     implement
    -0.56
    POSITIVE LOGITS
     ecru
    1.28
     swarovski
    1.25
     unwarran
    1.19
     ibiza
    1.17
     bandung
    1.16
     hairc
    1.14
     hoody
    1.14
     Minang
    1.13
     maneu
    1.12
     unspeak
    1.11
    Activations Density 0.395%

    No Known Activations