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. 8270
    Prev
    Next
    INDEX
    Explanations

    mentions of atheism and atheists

    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
    538
    +0.12
    0.4%
    938
    +0.10
    0.3%
    629
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    538
    +0.12
    0.02
    314
    +0.10
    0.01
    625
    +0.10
    0.02
    Negative Logits
     CWE
    -0.72
     himo
    -0.61
     Himo
    -0.60
    MessageOf
    -0.58
     gela
    -0.58
    FieldDescriptor
    -0.57
     fieldNum
    -0.57
    CopyWith
    -0.57
     ***!
    -0.57
    OGND
    -0.56
    POSITIVE LOGITS
     Athe
    1.07
     atheists
    1.03
     atheist
    0.97
    Athe
    0.95
     gaily
    0.93
     atheism
    0.93
     Mlle
    0.92
     McLaugh
    0.90
     pamph
    0.89
     athe
    0.89
    Activations Density 0.084%

    No Known Activations