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. 15680
    Prev
    Next
    INDEX
    Explanations

    phrases related to military operations and governmental regulations

    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
    227
    +0.18
    0.6%
    1499
    +0.17
    0.5%
    1343
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.18
    0.09
    1499
    +0.17
    0.08
    855
    +0.14
    0.05
    Negative Logits
    <bos>
    -0.92
     aneur
    -0.78
     aneurysm
    -0.74
     epithe
    -0.73
     sunburn
    -0.73
     larynx
    -0.71
     hypotension
    -0.70
     glandular
    -0.69
     fleshy
    -0.69
     dewy
    -0.68
    POSITIVE LOGITS
     fup
    1.78
     §.
    1.71
     Chapitre
    1.69
     rafra
    1.62
     fep
    1.61
     Lég
    1.61
     sii
    1.58
     »>
    1.56
     hcm
    1.56
     Présentation
    1.56
    Activations Density 0.466%

    No Known Activations