© 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. 4661
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions, involvement, or influence

    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
    1276
    +0.11
    0.4%
    994
    +0.11
    0.3%
    897
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.11
    0.05
    228
    +0.11
    0.04
    321
    +0.10
    0.04
    Negative Logits
     seng
    -0.52
     sendi
    -0.50
     bunda
    -0.49
    masta
    -0.49
     seksi
    -0.48
    fita
    -0.48
     krim
    -0.47
     pép
    -0.47
     arras
    -0.46
     HasFactory
    -0.46
    POSITIVE LOGITS
     call
    1.04
     CALL
    0.92
     Call
    0.90
    call
    0.89
     calls
    0.89
     calling
    0.88
    calls
    0.86
     disreg
    0.86
     Calls
    0.85
    calling
    0.84
    Activations Density 0.147%

    No Known Activations