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. 748
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific dates, names, locations, and historical events

    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
    +0.32
    1.9%
    1984
    +0.14
    0.9%
    1896
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.32
    0.19
    1034
    +0.14
    0.14
    1896
    +0.12
    0.12
    Negative Logits
    <bos>
    -3.47
    ⓧ
    -0.76
     découvre
    -0.70
    ///**
    -0.68
     préfère
    -0.64
    <?
    -0.63
    
    
    -0.62
    //----
    -0.61
    //---
    -0.61
     ressemble
    -0.61
    POSITIVE LOGITS
     véhic
    1.12
     catég
    1.04
     soulign
    1.04
     conflic
    1.00
     considér
    0.99
     sappi
    0.97
     marea
    0.96
     unlaw
    0.95
     valencia
    0.95
     délib
    0.94
    Activations Density 1.178%

    No Known Activations