© 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. 2123
    Prev
    Next
    INDEX
    Explanations

    references to revenge and payback

    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
    130
    +0.10
    0.3%
    1778
    +0.09
    0.3%
    74
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.10
    0.03
    549
    +0.09
    0.03
    1854
    +0.08
    0.02
    Negative Logits
     utop
    -1.03
     verba
    -1.01
     impon
    -1.00
     meras
    -1.00
     kram
    -0.94
     solidar
    -0.92
     stoff
    -0.91
     dras
    -0.89
     makro
    -0.87
     geolog
    -0.86
    POSITIVE LOGITS
     revenge
    0.91
     vengeance
    0.88
     venge
    0.87
     Revenge
    0.86
    revenge
    0.82
     mécanisme
    0.81
     pamph
    0.80
    Revenge
    0.78
     avenge
    0.77
     retribution
    0.75
    Activations Density 0.171%

    No Known Activations