© 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. 13390
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership positions or 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
    1793
    +0.14
    0.5%
    376
    +0.13
    0.5%
    122
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1793
    +0.14
    0.04
    376
    +0.13
    0.04
    650
    +0.12
    0.03
    Negative Logits
    becker
    -0.50
     smtplib
    -0.49
    autogui
    -0.49
     Sympathi
    -0.48
     fringed
    -0.48
     pettico
    -0.47
    colourful
    -0.46
    hever
    -0.45
     cami
    -0.44
     tutu
    -0.44
    POSITIVE LOGITS
    head
    1.23
    Head
    1.22
     head
    1.21
     Head
    1.18
     HEAD
    1.12
    HEAD
    1.05
     heads
    1.01
    heads
    0.97
     Heads
    0.91
    Heads
    0.87
    Activations Density 0.048%

    No Known Activations