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. 10121
    Prev
    Next
    INDEX
    Explanations

    references to editors and chief editors of newspapers or publications

    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
    544
    +0.13
    0.4%
    321
    +0.12
    0.4%
    1870
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.13
    0.03
    410
    +0.12
    0.02
    576
    +0.12
    0.02
    Negative Logits
    ഊ
    -0.52
    ഐ
    -0.51
    Demografía
    -0.50
     INVENTION
    -0.50
    icestershire
    -0.50
    leyeb
    -0.47
    قایناقلار
    -0.47
    BagLayout
    -0.47
    ഔ
    -0.47
    Litteratur
    -0.43
    POSITIVE LOGITS
     editor
    1.25
     Editor
    1.17
     editors
    1.17
    editor
    1.11
     Editors
    1.10
    Editor
    1.00
     editorial
    0.95
     EDITOR
    0.95
    editors
    0.94
     edits
    0.90
    Activations Density 0.044%

    No Known Activations