© 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. 6871
    Prev
    Next
    INDEX
    Explanations

    names containing 'Ken'

    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
    1222
    +0.14
    0.6%
    765
    +0.13
    0.6%
    555
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    765
    +0.14
    0.02
    981
    +0.13
    0.03
    1575
    +0.13
    0.02
    Negative Logits
     forbade
    -0.51
     Willoughby
    -0.49
     impelled
    -0.49
     gratify
    -0.49
     disapproved
    -0.47
     plundered
    -0.46
     endeavouring
    -0.45
    başı
    -0.43
     renounced
    -0.42
     rejoiced
    -0.42
    POSITIVE LOGITS
     KEN
    1.47
     Ken
    1.40
    Ken
    1.38
     ken
    1.28
    KEN
    1.09
     Kenneth
    1.03
    Kenneth
    1.00
    ken
    0.94
     KENN
    0.93
     Kenny
    0.93
    Activations Density 0.102%

    No Known Activations