© 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. 6540
    Prev
    Next
    INDEX
    Explanations

    phrases related to political ideology and loyalty

    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
    1403
    +0.09
    0.3%
    1965
    +0.08
    0.2%
    776
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1622
    +0.09
    0.03
    1575
    +0.08
    0.04
    1441
    +0.08
    0.04
    Negative Logits
     vété
    -1.12
     malheureux
    -1.10
     étrang
    -1.07
     clô
    -0.99
     automne
    -0.96
     merveilleux
    -0.96
     dégust
    -0.95
     appui
    -0.95
     bâton
    -0.95
     fantaisie
    -0.94
    POSITIVE LOGITS
     thing
    0.91
     goal
    0.76
     reason
    0.76
     aim
    0.68
     objective
    0.68
    satunya
    0.67
     question
    0.66
     challenge
    0.65
     requirement
    0.65
     issue
    0.65
    Activations Density 0.278%

    No Known Activations