© 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. 4398
    Prev
    Next
    INDEX
    Explanations

    references to chocolate and related sweet treats

    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
    120
    +0.13
    0.5%
    314
    +0.13
    0.5%
    1407
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.13
    0.02
    314
    +0.13
    0.01
    1407
    +0.12
    0.01
    Negative Logits
     tarte
    -0.79
     meras
    -0.71
     parma
    -0.71
     pican
    -0.69
     Siria
    -0.69
     coq
    -0.67
     Perp
    -0.65
     oreo
    -0.64
     coti
    -0.64
     suco
    -0.62
    POSITIVE LOGITS
     chocolate
    1.22
    chocolate
    1.13
     Chocolate
    1.11
    Chocolate
    1.08
     chocolates
    0.95
    OCOLATE
    0.81
    🍫
    0.76
     cocoa
    0.75
    colates
    0.65
    choco
    0.63
    Activations Density 0.070%

    No Known Activations