© 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. 7294
    Prev
    Next
    INDEX
    Explanations

    words related to work and leadership roles

    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
    1647
    +0.08
    0.2%
    223
    +0.07
    0.2%
    166
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1317
    +0.08
    0.04
    693
    +0.07
    0.03
    223
    +0.06
    0.02
    Negative Logits
     Juf
    -0.96
     Gorb
    -0.89
     kram
    -0.85
     Nö
    -0.85
     Schrö
    -0.84
     maksi
    -0.81
     Cik
    -0.79
     Strö
    -0.77
     Augu
    -0.77
     Hej
    -0.76
    POSITIVE LOGITS
     stressful
    0.68
    <bos>
    0.62
     Spandex
    0.59
     svat
    0.56
     Headaches
    0.52
     tricot
    0.51
     rewarding
    0.50
     rewards
    0.50
    lastung
    0.48
     lifestyle
    0.48
    Activations Density 0.495%

    No Known Activations