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. 10-RES-JB
    6. 861
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the Devil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    68
    +0.14
    0.8%
    370
    +0.13
    0.7%
    687
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.14
    0.06
    1741
    +0.13
    0.00
    1870
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.54
    Примеча
    -0.68
    RunWith
    -0.67
    Asoci
    -0.66
    Hå
    -0.65
    Ingredi
    -0.65
    Continu
    -0.65
    Enllaces
    -0.64
    elemField
    -0.64
    ുറ
    -0.64
    POSITIVE LOGITS
     Montagne
    1.11
    .-"
    0.98
     ?...
    0.95
     miu
    0.95
     !'
    0.95
     !...
    0.94
     nant
    0.94
     salat
    0.93
     lii
    0.93
     frankfurt
    0.93
    Activations Density 0.397%

    No Known Activations