Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15302
    Prev
    Next
    INDEX
    Explanations

    information related to verification, approval, and confirmation processes

    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
    0.9%
    478
    +0.08
    0.5%
    1142
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1142
    +0.17
    0.08
    1479
    +0.08
    0.07
    30
    +0.07
    0.07
    Negative Logits
    <bos>
    -3.83
    <?
    -0.71
    displayquote
    -0.70
    /***
    
    -0.70
    //{
    
    -0.69
    Referències
    -0.68
    })();
    
    -0.67
    
    
    -0.67
     make
    -0.63
     pay
    -0.63
    POSITIVE LOGITS
     stockholm
    1.84
     lidl
    1.70
     chrysler
    1.55
     eiffel
    1.53
     maneu
    1.51
     michelin
    1.50
     riviera
    1.48
     cabrio
    1.48
     hilton
    1.47
     liverpool
    1.47
    Activations Density 1.480%

    No Known Activations