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. 8213
    Prev
    Next
    INDEX
    Explanations

    descriptions related to financial budgeting and deficit management

    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
    +0.22
    0.8%
    1499
    +0.12
    0.4%
    604
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.22
    0.10
    1253
    +0.12
    0.03
    1519
    +0.08
    0.06
    Negative Logits
    <bos>
    -3.15
     intersper
    -1.38
     encomp
    -1.22
    ⓧ
    -1.15
    
    
    -1.12
     reconno
    -1.10
    <?
    -1.08
    /**
    -1.07
     gild
    -1.06
    /***
    
    -1.05
    POSITIVE LOGITS
     tanong
    1.04
     sarili
    0.96
     jawa
    0.96
     bandung
    0.95
     susun
    0.94
     sapat
    0.94
     kani
    0.88
     bagay
    0.87
     bahay
    0.86
     Jambi
    0.85
    Activations Density 1.034%

    No Known Activations