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. 15834
    Prev
    Next
    INDEX
    Explanations

    references to Muslim individuals or groups in various 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
    1942
    +0.15
    0.5%
    1331
    +0.13
    0.4%
    406
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1942
    +0.15
    0.04
    1331
    +0.13
    0.03
    68
    +0.12
    0.03
    Negative Logits
    marginVertical
    -0.52
    marginHorizontal
    -0.51
    paddingVertical
    -0.50
    borderBottom
    -0.49
    fjspx
    -0.47
     dovrebbero
    -0.47
     AppColors
    -0.44
    borderTop
    -0.44
    Chandigarh
    -0.44
     lanka
    -0.44
    POSITIVE LOGITS
     Muslim
    1.01
     Mónica
    0.98
    Muslim
    0.97
     Muslims
    0.96
     Darío
    0.94
     McLaugh
    0.91
     Mlle
    0.87
    Muslims
    0.86
     Crespo
    0.86
     Áng
    0.85
    Activations Density 0.062%

    No Known Activations