© 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. 15176
    Prev
    Next
    INDEX
    Explanations

    politically related phrases and names

    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
    50
    +0.18
    0.6%
    752
    +0.17
    0.5%
    1967
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.18
    0.04
    16
    +0.17
    0.04
    50
    +0.11
    0.04
    Negative Logits
    Ikr
    -0.81
     viciss
    -0.79
    !!</
    -0.77
    ;;)
    -0.73
    /**
    -0.72
     jajaja
    -0.70
     fufficient
    -0.69
     shewn
    -0.68
    Hahah
    -0.67
    Lmfao
    -0.66
    POSITIVE LOGITS
    Etimo
    0.49
     ...
    0.47
    İş
    0.46
     its
    0.44
    Revenir
    0.44
    +#+
    0.44
    Iain
    0.43
    minente
    0.43
    leveland
    0.43
    Çok
    0.42
    Activations Density 0.178%

    No Known Activations