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. 15375
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to overseeing, managing, and supervising in a professional context

    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
    156
    +0.09
    0.3%
    1407
    +0.08
    0.2%
    1009
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.09
    0.04
    1336
    +0.08
    0.04
    1407
    +0.08
    0.03
    Negative Logits
     faço
    -0.46
     localizar
    -0.45
    cesz
    -0.44
    <bos>
    -0.43
    d
    -0.42
    usstsein
    -0.42
    изнь
    -0.42
     donnera
    -0.42
    nosotros
    -0.41
     също
    -0.41
    POSITIVE LOGITS
     aquarelle
    0.94
     peppa
    0.92
     bordeaux
    0.90
     indestru
    0.89
     murano
    0.88
     doman
    0.87
     tremb
    0.85
     napoli
    0.85
     embodi
    0.84
     cabrio
    0.84
    Activations Density 0.238%

    No Known Activations