© 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. 15222
    Prev
    Next
    INDEX
    Explanations

    references to theatrical venues

    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
    1133
    +0.12
    0.5%
    1778
    +0.12
    0.5%
    1392
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.12
    0.02
    1133
    +0.12
    0.02
    1392
    +0.12
    0.02
    Negative Logits
     accla
    -0.60
     Sén
    -0.57
     Docteur
    -0.53
     carbone
    -0.51
     bourg
    -0.51
     toul
    -0.50
     Classe
    -0.49
     Carga
    -0.48
     vinyle
    -0.48
    onymus
    -0.48
    POSITIVE LOGITS
     theater
    1.25
     theatre
    1.21
     Theater
    1.12
     Theatre
    1.11
     theaters
    1.10
    theatre
    1.08
    theater
    1.04
    Theatre
    1.03
     theatres
    1.02
    Theater
    1.02
    Activations Density 0.086%

    No Known Activations