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. 560
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and legislative discussions

    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
    1120
    +0.11
    0.3%
    792
    +0.09
    0.3%
    511
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.11
    0.03
    1380
    +0.09
    0.00
    851
    +0.09
    0.01
    Negative Logits
    Carreira
    -0.87
     onAnimation
    -0.87
    Serviço
    -0.85
    مراجع
    -0.83
    المراجع
    -0.82
    التالي
    -0.81
    都係
    -0.80
    منابع
    -0.79
    Referências
    -0.79
     significantly
    -0.78
    POSITIVE LOGITS
     impra
    3.06
     affor
    2.99
     unden
    2.91
     scrat
    2.89
     unlaw
    2.87
     reluct
    2.87
     suscep
    2.86
     disreg
    2.81
     disagre
    2.78
     strick
    2.75
    Activations Density 0.371%

    No Known Activations