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. 2853
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial and corporate influence in politics and policy-making

    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
    198
    +0.17
    0.5%
    604
    +0.09
    0.2%
    1143
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.17
    0.07
    1143
    +0.09
    0.03
    1360
    +0.08
    0.04
    Negative Logits
    <bos>
    -0.57
     apprehen
    -0.56
     shenan
    -0.51
     appreci
    -0.48
    Rgds
    -0.45
     ministres
    -0.44
     willy
    -0.44
     ineffec
    -0.43
     exasper
    -0.42
     chanced
    -0.41
    POSITIVE LOGITS
     soggior
    0.76
     autunno
    0.66
     palio
    0.66
     corrom
    0.64
     Aéroport
    0.63
     pranzo
    0.62
     lusso
    0.62
     cavallo
    0.62
     prenota
    0.61
     Muhamma
    0.61
    Activations Density 0.449%

    No Known Activations