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. 665
    Prev
    Next
    INDEX
    Explanations

    mentions of voters and voting-related 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
    +0.17
    0.8%
    484
    +0.10
    0.5%
    1350
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.17
    0.07
    486
    +0.10
    0.05
    168
    +0.10
    0.06
    Negative Logits
    <bos>
    -3.04
    /***
    
    -1.02
    
    
    -0.90
    Vegeu
    -0.90
    /**
    -0.87
    ⓧ
    -0.87
    <?
    -0.80
    lateinit
    -0.73
    Enllaços
    -0.71
    //};
    -0.69
    POSITIVE LOGITS
     stockholm
    1.23
     riviera
    1.23
     chrysler
    1.13
     tucson
    1.12
     eiffel
    1.10
     toledo
    1.09
     munich
    1.08
     riva
    1.08
     seoul
    1.07
     ecru
    1.05
    Activations Density 0.453%

    No Known Activations