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. 15247
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical events and international diplomacy

    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
    214
    +0.13
    0.5%
    596
    +0.13
    0.5%
    1637
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.13
    0.05
    596
    +0.13
    0.04
    303
    +0.12
    0.04
    Negative Logits
     habang
    -0.61
     itong
    -0.59
     vī
    -0.58
     siyang
    -0.57
     kapag
    -0.57
    ējās
    -0.54
     vairāk
    -0.54
     bēr
    -0.52
     susun
    -0.51
     akong
    -0.51
    POSITIVE LOGITS
     —
    0.76
    ”—
    0.66
    ercice
    0.62
    —
    0.59
    !—
    0.57
    ——
    0.57
    )—
    0.57
     toscana
    0.57
    .—
    0.55
    .”—
    0.55
    Activations Density 0.164%

    No Known Activations