© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12464
    Prev
    Next
    INDEX
    Explanations

    statements related to the sustainability of various aspects of society, including topics like education, economy, lifestyle, and environmental issues

    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
    1047
    +0.14
    0.5%
    976
    +0.11
    0.4%
    1870
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1047
    +0.14
    0.02
    976
    +0.11
    0.02
    938
    +0.10
    0.02
    Negative Logits
    Abbiamo
    -0.71
     revan
    -0.70
    Molto
    -0.69
    Allora
    -0.65
    Siamo
    -0.65
     colloc
    -0.64
     poichè
    -0.63
    Più
    -0.62
     reluct
    -0.62
    Oltre
    -0.59
    POSITIVE LOGITS
     sustainable
    1.24
     sustainability
    1.21
     Sustainable
    1.09
     Sustainability
    1.06
    sustainable
    1.06
    Sustainable
    1.05
    ustainable
    1.04
     sustain
    1.04
     SUSTAIN
    1.01
    Sustainability
    1.01
    Activations Density 0.067%

    No Known Activations