© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7909
    Prev
    Next
    INDEX
    Explanations

    phrases related to weight loss, diet, and body transformation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    0.9%
    1978
    +0.08
    0.3%
    62
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1530
    +0.24
    0.05
    74
    +0.08
    0.03
    1221
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.96
    
    -0.73
    ⓧ
    -0.69
    /***
    -0.66
    ///**
    -0.60
    setClass
    -0.57
     abolish
    -0.54
    qiao
    -0.54
     ratify
    -0.51
     transact
    -0.50
    POSITIVE LOGITS
     kristal
    1.03
     karton
    1.02
     moza
    1.01
     seksi
    1.01
     lele
    1.00
     meis
    0.99
     Minang
    0.98
     keram
    0.97
     ananas
    0.97
     kafe
    0.96
    Activations Density 0.469%

    No Known Activations