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. 15904
    Prev
    Next
    INDEX
    Explanations

    situations involving legal rulings and community actions

    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
    1577
    +0.30
    1.0%
    394
    +0.17
    0.6%
    1842
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.30
    0.05
    1577
    +0.17
    0.14
    1662
    +0.12
    0.09
    Negative Logits
     shenan
    -1.89
     reluct
    -1.82
     encomp
    -1.78
     apprehen
    -1.77
     disagre
    -1.74
     depic
    -1.70
     maneu
    -1.63
     accla
    -1.59
     intersper
    -1.58
     uninten
    -1.57
    POSITIVE LOGITS
     typelib
    0.75
    TintMode
    0.74
    StoryboardSegue
    0.74
    RegressionTest
    0.72
    GeoNames
    0.69
    writeFieldEnd
    0.69
     الرياضيه
    0.68
     CiNii
    0.67
    twimg
    0.67
     betweenstory
    0.66
    Activations Density 2.545%

    No Known Activations