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. 2398
    Prev
    Next
    INDEX
    Explanations

    descriptions related to real estate listings, particularly focusing on features like kitchens and counters

    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
    +0.21
    1.3%
    325
    +0.08
    0.5%
    1013
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.21
    0.03
    1971
    +0.08
    0.03
    325
    +0.08
    0.03
    Negative Logits
    <bos>
    -3.28
    /**
    -1.20
    ⓧ
    -1.13
    <?
    -1.10
    /***
    
    -1.02
    
    
    -1.01
    <?
    
    -0.85
    /*
    -0.82
     mobilize
    -0.78
     endow
    -0.75
    POSITIVE LOGITS
     Juf
    1.06
    Kitchen
    1.01
     kitchen
    1.01
     riva
    1.01
     Keny
    0.97
    kitchen
    0.96
     thuy
    0.92
     Kitchen
    0.90
     éto
    0.89
     Minang
    0.89
    Activations Density 0.084%

    No Known Activations