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. 15727
    Prev
    Next
    INDEX
    Explanations

    references to philosophical concepts related to theology and metaphysics

    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
    1446
    +0.10
    0.3%
    1871
    +0.09
    0.3%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1446
    +0.10
    0.03
    509
    +0.09
    0.04
    1380
    +0.09
    0.02
    Negative Logits
     stratigraph
    -0.79
     akut
    -0.74
     impra
    -0.72
     depic
    -0.72
     uhr
    -0.71
     ekos
    -0.70
     panik
    -0.69
     optik
    -0.69
     Teknik
    -0.69
     antik
    -0.69
    POSITIVE LOGITS
     Dumnezeu
    0.59
     commandement
    0.59
     trésor
    0.56
     mécanisme
    0.55
     établissement
    0.54
     bénéfice
    0.54
    Dacă
    0.53
     laboratoire
    0.52
     partenariat
    0.52
     itinéraire
    0.52
    Activations Density 0.254%

    No Known Activations