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. 2926
    Prev
    Next
    INDEX
    Explanations

    mentions of things being precious or valuable

    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
    25
    +0.13
    0.4%
    871
    +0.12
    0.4%
    478
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    871
    +0.13
    0.03
    25
    +0.12
    0.03
    1839
    +0.11
    0.03
    Negative Logits
    styleType
    -0.57
    hObject
    -0.51
    __':
    -0.50
    ニューアル
    -0.50
    __":
    -0.49
    Šaltiniai
    -0.45
    usiai
    -0.45
    CellStyle
    -0.44
    MLLoader
    -0.44
    OnDelete
    -0.43
    POSITIVE LOGITS
     Valuable
    0.94
     valuable
    0.94
     precious
    0.92
     Precious
    0.86
    valuable
    0.85
    Precious
    0.82
    precious
    0.78
     priceless
    0.74
     invaluable
    0.72
     valuables
    0.70
    Activations Density 0.123%

    No Known Activations