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. 3073
    Prev
    Next
    INDEX
    Explanations

    references to company names and stock market related terms

    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
    1343
    +0.16
    0.5%
    227
    +0.14
    0.4%
    1177
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.03
    934
    +0.14
    0.01
    77
    +0.11
    0.02
    Negative Logits
    <bos>
    -1.11
    stdarg
    -0.72
     paraît
    -0.65
    excelente
    -0.63
    daß
    -0.62
    PushMatrix
    -0.60
    Çok
    -0.60
    Estou
    -0.59
     mène
    -0.59
    einen
    -0.58
    POSITIVE LOGITS
     Keny
    0.96
     Ferdin
    0.92
     ritard
    0.92
     Middles
    0.91
     panik
    0.88
     trö
    0.88
     reuters
    0.87
     accla
    0.87
     stockholm
    0.86
     volunte
    0.86
    Activations Density 0.094%

    No Known Activations