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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 223
    Prev
    Next
    INDEX
    Explanations

    connections between individuals and their social or political contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    509
    +0.09
    0.3%
    764
    +0.09
    0.3%
    1294
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1294
    +0.09
    0.03
    1362
    +0.09
    0.01
    1808
    +0.09
    0.03
    Negative Logits
     kram
    -0.79
     tyn
    -0.74
     traktor
    -0.69
     laf
    -0.67
     Arxiv
    -0.64
     ciga
    -0.63
     brutto
    -0.62
     makro
    -0.62
     plak
    -0.61
     ert
    -0.61
    POSITIVE LOGITS
     later
    1.00
    later
    0.91
    Later
    0.90
     Later
    0.77
     senere
    0.71
     LATER
    0.70
     posteriormente
    0.69
     subsequent
    0.68
     eventually
    0.65
     später
    0.65
    Activations Density 0.266%

    No Known Activations