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. 15964
    Prev
    Next
    INDEX
    Explanations

    references to specific regulations and legal provisions

    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
    732
    +0.12
    0.4%
    897
    +0.11
    0.4%
    1983
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    732
    +0.12
    0.04
    1983
    +0.11
    0.04
    1034
    +0.10
    0.04
    Negative Logits
    công
    -0.47
    iParam
    -0.47
    intelligible
    -0.47
    làm
    -0.46
    ยม
    -0.46
    AdapterView
    -0.46
    AreEqual
    -0.46
    ie
    -0.45
    Tác
    -0.44
    split
    -0.44
    POSITIVE LOGITS
     UNDER
    1.12
     Under
    1.09
     hcm
    1.08
    Under
    1.07
    under
    1.00
     inder
    0.99
    UNDER
    0.99
     under
    0.98
     Bajo
    0.98
     Aéroport
    0.94
    Activations Density 0.066%

    No Known Activations