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. 15920
    Prev
    Next
    INDEX
    Explanations

    information related to medical conditions and surgeries, particularly focusing on a specific condition involving nerve cells in the intestinal muscles causing blockages

    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
    1967
    +0.20
    0.6%
    198
    +0.20
    0.6%
    1842
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.20
    0.06
    1842
    +0.20
    0.05
    766
    +0.17
    0.04
    Negative Logits
     accla
    -2.29
     reluct
    -2.24
     inev
    -2.19
     encomp
    -2.16
     disagre
    -2.16
     depic
    -2.15
     ftu
    -2.14
     shenan
    -2.14
     Intere
    -2.11
     increa
    -2.11
    POSITIVE LOGITS
    Geplaatst
    0.68
    <bos>
    0.67
    )
    0.61
     آمریک
    0.59
     lenker
    0.58
    ctrons
    0.58
    rrggbb
    0.58
     usually
    0.57
    的意思
    0.57
    헌
    0.57
    Activations Density 0.425%

    No Known Activations