© 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. 12535
    Prev
    Next
    INDEX
    Explanations

    events or actions that begin or start

    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
    1392
    +0.10
    0.3%
    1336
    +0.08
    0.2%
    1276
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1392
    +0.10
    0.05
    1336
    +0.08
    0.05
    680
    +0.08
    0.03
    Negative Logits
     lara
    -0.78
     tew
    -0.78
     purcha
    -0.77
     meis
    -0.74
     attemp
    -0.74
     emphat
    -0.74
     kuro
    -0.73
     „,
    -0.72
     fte
    -0.72
     pooh
    -0.72
    POSITIVE LOGITS
     started
    0.96
     starts
    0.88
    started
    0.88
     start
    0.87
     starting
    0.84
     began
    0.82
     beginning
    0.82
     begun
    0.81
     begin
    0.81
     begins
    0.80
    Activations Density 0.182%

    No Known Activations