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. 891
    Prev
    Next
    INDEX
    Explanations

    phrases related to college and educational activities

    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
    +0.28
    1.7%
    678
    +0.07
    0.4%
    1177
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1510
    +0.28
    0.12
    144
    +0.07
    0.15
    1385
    +0.07
    0.20
    Negative Logits
    <bos>
    -3.15
    ⓧ
    -1.25
    /**
    -1.04
    <?
    -0.96
    
    
    -0.92
    /*
    -0.90
    .
    -0.83
     ensure
    -0.79
     put
    -0.78
    /*++
    -0.78
    POSITIVE LOGITS
     Juf
    2.31
     Minang
    2.04
     Augu
    1.94
     Keny
    1.92
     embodi
    1.91
     Intere
    1.89
     sovere
    1.87
     emphat
    1.84
     véhic
    1.83
     affor
    1.82
    Activations Density 3.743%

    No Known Activations