© 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. 12493
    Prev
    Next
    INDEX
    Explanations

    references to commitments and pledges within political contexts

    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
    +0.14
    0.5%
    860
    +0.12
    0.4%
    812
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    860
    +0.14
    0.03
    124
    +0.12
    0.03
    1516
    +0.11
    0.02
    Negative Logits
     volunte
    -1.08
     reluct
    -1.07
     disagre
    -1.06
     indestru
    -1.05
     accla
    -1.05
     emphat
    -1.02
     shenan
    -1.02
     unlaw
    -1.00
     disgra
    -0.99
     coö
    -0.99
    POSITIVE LOGITS
     commitment
    1.50
     commitments
    1.34
     committed
    1.34
     Commitment
    1.30
     commit
    1.25
    commitment
    1.23
    commit
    1.19
    Commitment
    1.19
    committed
    1.14
     Commit
    1.13
    Activations Density 0.044%

    No Known Activations