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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11320
    Prev
    Next
    INDEX
    Explanations

    initials and acronyms for various organizations and states as well as the names of the organization types themselves

    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
    +0.37
    2.5%
    1535
    +0.04
    0.3%
    1446
    +0.04
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1403
    +0.37
    0.22
    15
    +0.04
    0.23
    674
    +0.04
    0.23
    Negative Logits
    ,
    -1.35
    .
    -1.09
     and
    -1.08
     belliger
    -1.05
     (
    -1.05
     massacres
    -1.02
     in
    -1.00
     
    -1.00
     or
    -0.98
     despotism
    -0.98
    POSITIVE LOGITS
    <bos>
    12.93
    GEBURTSDATUM
    2.40
     betweenstory
    2.37
    expandindo
    2.34
    Autoritní
    2.19
    تقاوى
    1.99
     '\\;'
    1.94
     kasarigan
    1.94
     Italijani
    1.94
     дописавши
    1.89
    Activations Density 0.084%

    No Known Activations