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. 13500
    Prev
    Next
    INDEX
    Explanations

    words related to Lebanon, Hezbollah, and conflicts in the region

    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
    1137
    +0.15
    0.6%
    517
    +0.15
    0.6%
    411
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.15
    0.02
    227
    +0.15
    0.03
    1177
    +0.11
    0.02
    Negative Logits
    Apre
    -0.47
     كومونز
    -0.45
    Brak
    -0.44
     Normdatei
    -0.44
    Trotz
    -0.44
     birdie
    -0.44
    rítica
    -0.43
    Pase
    -0.43
    Ян
    -0.42
    Conteúdo
    -0.42
    POSITIVE LOGITS
     Lebanon
    1.11
    Lebanon
    1.07
     Lebanese
    0.93
    bollah
    0.92
     Hezbollah
    0.91
     Beirut
    0.82
    Leb
    0.79
     LeBlanc
    0.70
     Leb
    0.69
     Liban
    0.69
    Activations Density 0.159%

    No Known Activations