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. 16072
    Prev
    Next
    INDEX
    Explanations

    details related to technical issues, accidents, or incidents involving machinery or transportation

    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
    599
    +0.10
    0.3%
    1166
    +0.10
    0.3%
    855
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    862
    +0.10
    0.02
    2000
    +0.10
    0.04
    1438
    +0.10
    0.03
    Negative Logits
     pama
    -0.98
     panik
    -0.97
     silikon
    -0.96
     keramik
    -0.94
     Komun
    -0.94
     Meksi
    -0.92
     karton
    -0.92
     kask
    -0.87
     seksi
    -0.86
     susun
    -0.85
    POSITIVE LOGITS
     itself
    0.72
    itself
    0.62
     Itself
    0.57
     tupperware
    0.54
     Wird
    0.53
    ENODEV
    0.51
     tricot
    0.51
    ConstraintMaker
    0.48
     plais
    0.48
     époux
    0.46
    Activations Density 0.804%

    No Known Activations