© 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 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. 10810
    Prev
    Next
    INDEX
    Explanations

    phrases related to political positions and advocacy

    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
    605
    +0.09
    0.3%
    420
    +0.09
    0.3%
    1157
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1586
    +0.09
    0.04
    1157
    +0.09
    0.04
    1897
    +0.08
    0.03
    Negative Logits
     nutella
    -0.65
     ingrat
    -0.62
     peppa
    -0.59
     tupperware
    -0.58
     insensible
    -0.58
     withal
    -0.57
     effectually
    -0.57
     scrat
    -0.56
     inconce
    -0.55
     discolor
    -0.54
    POSITIVE LOGITS
    fillText
    0.53
    PositiveButton
    0.52
    Selección
    0.49
     favour
    0.49
    Nuorodos
    0.48
    Aceite
    0.47
     AGAINST
    0.47
     favor
    0.47
    Trichlor
    0.46
    Ilustra
    0.46
    Activations Density 0.213%

    No Known Activations