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. 483
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical tensions and sanctions

    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
    604
    +0.17
    0.5%
    939
    +0.10
    0.3%
    1120
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.17
    0.07
    1499
    +0.10
    0.06
    1948
    +0.10
    0.05
    Negative Logits
     intersper
    -1.46
     impra
    -1.36
     apprehen
    -1.33
     disagre
    -1.32
     reluct
    -1.32
     gaily
    -1.31
     inconce
    -1.31
     unspeak
    -1.31
     shenan
    -1.29
     uninten
    -1.27
    POSITIVE LOGITS
     sanctions
    0.67
    Economía
    0.56
    krivelse
    0.53
     >=",
    0.52
    ISupport
    0.52
     embargo
    0.52
     diplomatic
    0.51
    mbito
    0.51
     hábit
    0.51
     Naciones
    0.50
    Activations Density 0.503%

    No Known Activations