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. 5416
    Prev
    Next
    INDEX
    Explanations

    dates and specific events in a university setting

    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
    1451
    +0.12
    0.7%
    1413
    +0.11
    0.6%
    1937
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.12
    283
    +0.11
    0.00
    1741
    +0.11
    -0.01
    Negative Logits
    <bos>
    -2.02
    
    
    -0.91
    <?
    -0.80
     intersper
    -0.78
    uckoo
    -0.75
    ougars
    -0.74
     gratify
    -0.73
     superintend
    -0.72
    /***
    
    -0.70
    ⓧ
    -0.68
    POSITIVE LOGITS
     seksi
    1.06
     konserv
    1.04
     alkoh
    1.02
     saar
    1.01
     karton
    1.01
     silikon
    1.01
     kram
    1.00
     antik
    1.00
     kosme
    0.99
     kriminal
    0.98
    Activations Density 1.562%

    No Known Activations