© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 12
    Prev
    Next
    INDEX
    Explanations

    specific amusement park attractions related to a famous movie series

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.7%
    559
    +0.09
    0.3%
    971
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.20
    0.04
    1860
    +0.09
    0.04
    138
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.63
    ⓧ
    -0.96
    /**
    -0.75
    
    -0.74
    <?
    -0.74
    SequentialGroup
    -0.74
     initComponents
    -0.74
    HasIndex
    -0.73
    зулта
    -0.72
     jsPsych
    -0.71
    POSITIVE LOGITS
     affor
    2.02
     maneu
    1.96
     increa
    1.88
     volunte
    1.83
     fortn
    1.81
     wien
    1.81
     impra
    1.79
     fta
    1.78
     stockholm
    1.77
     strick
    1.77
    Activations Density 0.209%

    No Known Activations