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. 1440
    Prev
    Next
    INDEX
    Explanations

    phrases related to warnings or advice

    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
    605
    +0.08
    0.2%
    198
    +0.08
    0.2%
    321
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1851
    +0.08
    0.04
    912
    +0.08
    0.04
    100
    +0.08
    0.04
    Negative Logits
     parlamento
    -0.57
    setLayoutParams
    -0.53
    PageFactory
    -0.52
     Siria
    -0.51
    emmel
    -0.51
    lccccc
    -0.50
     Rumania
    -0.50
    blurRadius
    -0.50
     Mâ
    -0.49
    JpaRepository
    -0.49
    POSITIVE LOGITS
    idać
    0.66
     bandai
    0.60
     leçon
    0.57
     pylab
    0.55
     wako
    0.54
    asteroide
    0.52
     underestimate
    0.52
     créativité
    0.52
     akong
    0.50
     épreuve
    0.50
    Activations Density 0.298%

    No Known Activations