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. 15365
    Prev
    Next
    INDEX
    Explanations

    commands and code snippets within text

    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
    1145
    +0.17
    0.8%
    1127
    +0.15
    0.7%
    1983
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.17
    0.05
    1145
    +0.15
    0.04
    1177
    +0.14
    0.02
    Negative Logits
     COP
    -0.51
     cop
    -0.47
    —
    -0.47
    شن
    -0.44
     Sk
    -0.43
    COP
    -0.43
     Sik
    -0.42
     DataLoader
    -0.42
     COPD
    -0.42
    voiture
    -0.42
    POSITIVE LOGITS
     ļ
    0.83
     paff
    0.78
     dispen
    0.78
     alkoh
    0.77
     hek
    0.75
     kram
    0.75
     mī
    0.74
     ftu
    0.74
     tille
    0.73
     mef
    0.73
    Activations Density 0.294%

    No Known Activations