© 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. 4315
    Prev
    Next
    INDEX
    Explanations

    words related to rapid change, growth, or deterioration

    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
    1870
    +0.13
    0.5%
    1896
    +0.12
    0.4%
    410
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1865
    +0.13
    0.02
    1506
    +0.12
    0.02
    410
    +0.11
    0.02
    Negative Logits
     extérieur
    -0.51
     sécurisé
    -0.48
     isolé
    -0.47
     extérieure
    -0.46
     abstrait
    -0.46
     fréquent
    -0.45
    Gemeinsame
    -0.44
     typique
    -0.44
     doté
    -0.44
     المعيارى
    -0.43
    POSITIVE LOGITS
     Rapid
    0.97
    Rapid
    0.96
     rapid
    0.96
     hecta
    0.91
    rapid
    0.90
     rapidly
    0.85
     nutella
    0.77
     chong
    0.74
     gonz
    0.74
     burberry
    0.73
    Activations Density 0.059%

    No Known Activations