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. 6082
    Prev
    Next
    INDEX
    Explanations

    references to economic stimulus packages

    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
    1065
    +0.15
    0.7%
    1045
    +0.12
    0.6%
    1896
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.15
    0.02
    1065
    +0.12
    0.02
    1045
    +0.11
    0.02
    Negative Logits
    <bos>
    -1.47
    
    
    -0.83
    ⓧ
    -0.67
    ContentAlignment
    -0.62
    มาะ
    -0.59
    <?
    
    -0.58
    /**
    -0.57
    rungsseite
    -0.56
    ↘
    -0.55
     Cro
    -0.54
    POSITIVE LOGITS
     Stimulus
    1.25
     stimulus
    1.24
     Stim
    1.10
     carrefour
    1.09
     stimulation
    1.08
    Stim
    1.08
     stimuli
    1.06
     Stimulation
    1.02
     bourg
    1.00
    stimulus
    1.00
    Activations Density 0.268%

    No Known Activations