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. 8250
    Prev
    Next
    INDEX
    Explanations

    phrases expressing emphasis or contrast

    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
    +0.13
    0.5%
    1150
    +0.09
    0.3%
    1042
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.13
    0.06
    1245
    +0.09
    0.06
    734
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.48
    <?
    
    -0.82
    /***
    
    -0.69
    MessageOf
    -0.65
     bezeichneter
    -0.63
    },{
    
    -0.62
    ⓧ
    -0.60
     propOrder
    -0.59
    
    
    -0.55
    /*!
    
    -0.55
    POSITIVE LOGITS
     maneu
    1.24
     disreg
    1.16
     [''
    1.08
     madonna
    1.05
     tupperware
    1.01
     uefa
    0.99
     reluct
    0.99
     jacques
    0.99
     disagre
    0.98
     strick
    0.98
    Activations Density 0.839%

    No Known Activations