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. 14831
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotions, particularly crying

    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
    0.8%
    1271
    +0.11
    0.5%
    1482
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1356
    +0.18
    0.02
    1568
    +0.11
    0.02
    624
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.84
    /***
    
    -0.74
    ⓧ
    -0.73
    CommonModule
    -0.61
    Παραπομπές
    -0.61
    ൊ
    -0.61
    <?
    -0.60
    ///**
    -0.60
    displayquote
    -0.59
    Đặc
    -0.59
    POSITIVE LOGITS
     cabrio
    1.30
     napoli
    1.28
     Juf
    1.28
     milano
    1.25
     bordeaux
    1.22
     stockholm
    1.22
     casio
    1.21
     riviera
    1.20
     lamborghini
    1.19
     wien
    1.19
    Activations Density 0.102%

    No Known Activations