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. 213
    Prev
    Next
    INDEX
    Explanations

    amenities and services offered by a hotel or accommodation

    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
    1068
    +0.15
    0.9%
    1323
    +0.14
    0.8%
    50
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1323
    +0.15
    0.04
    1068
    +0.14
    0.03
    58
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.57
    /**
    -0.92
    ⓧ
    -0.87
    
    
    -0.81
    <?
    -0.75
     Waarom
    -0.71
    <?
    
    -0.70
    /*
    -0.67
    /***
    
    -0.66
     disbur
    -0.64
    POSITIVE LOGITS
     En
    1.24
    En
    1.10
     EN
    1.00
     aen
    0.95
     en
    0.92
     compréhen
    0.91
     Minang
    0.88
     Enc
    0.88
     Ene
    0.88
     Ena
    0.86
    Activations Density 0.167%

    No Known Activations