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. 1412
    Prev
    Next
    INDEX
    Explanations

    the beginning of 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
    674
    +0.44
    5.6%
    1741
    +0.07
    0.8%
    1870
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.44
    0.32
    800
    +0.07
    0.34
    354
    +0.04
    0.33
    Negative Logits
     unspeak
    -2.94
     reluct
    -2.82
     disgra
    -2.72
     unlaw
    -2.71
     shenan
    -2.65
     impra
    -2.60
     impractica
    -2.60
     disagre
    -2.56
     ineffec
    -2.54
     horrend
    -2.53
    POSITIVE LOGITS
    <bos>
    14.50
    GEBURTSDATUM
    2.54
    expandindo
    2.53
     betweenstory
    2.50
    Autoritní
    2.47
    تقاوى
    2.21
     Italijani
    2.18
     Administrativna
    2.17
     Paglinawan
    2.15
     kasarigan
    2.12
    Activations Density 0.089%

    No Known Activations