© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16113
    Prev
    Next
    INDEX
    Explanations

    phrases related to political statements and activities

    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
    2019
    +0.22
    0.7%
    381
    +0.14
    0.5%
    1404
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1404
    +0.22
    0.08
    545
    +0.14
    0.06
    1472
    +0.10
    0.05
    Negative Logits
     mécanisme
    -0.73
    throwaway
    -0.68
    <bos>
    -0.68
     noyau
    -0.60
     biais
    -0.60
     maintien
    -0.60
    sneak
    -0.59
     consommate
    -0.58
     fameux
    -0.57
    colourful
    -0.56
    POSITIVE LOGITS
     venezuela
    0.87
     particolar
    0.85
     scatt
    0.82
     utop
    0.82
    fordable
    0.80
     venuto
    0.78
     inol
    0.78
     sappi
    0.78
     magis
    0.77
     fatis
    0.76
    Activations Density 0.219%

    No Known Activations