© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12506
    Prev
    Next
    INDEX
    Explanations

    sentences and proper nouns from news articles

    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
    +0.47
    4.2%
    1741
    +0.07
    0.7%
    381
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.47
    0.28
    1690
    +0.07
    0.28
    354
    +0.05
    0.28
    Negative Logits
     reluct
    -6.06
     increa
    -5.72
     impra
    -5.70
     disagre
    -5.67
     shenan
    -5.66
     unspeak
    -5.55
     indestru
    -5.49
     inev
    -5.41
     depic
    -5.39
     disgra
    -5.25
    POSITIVE LOGITS
    <bos>
    14.71
     betweenstory
    2.65
    GEBURTSDATUM
    2.59
    Autoritní
    2.57
    expandindo
    2.54
     Paglinawan
    2.54
     Italijani
    2.43
     Walkover
    2.38
     Administrativna
    2.35
    تقاوى
    2.33
    Activations Density 0.080%

    No Known Activations