© 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. 0-RES-JB
    11. 2936
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of death

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.10
    0.5%
    1296
    +0.07
    0.3%
    1671
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1173
    +0.10
    0.04
    265
    +0.07
    0.04
    1061
    +0.06
    0.04
    Negative Logits
    <bos>
    -2.01
    public
    -0.77
    const
    -0.73
    private
    -0.71
     continue
    -0.68
     assume
    -0.68
    ,
    -0.67
    @
    -0.66
    //
    -0.66
    let
    -0.66
    POSITIVE LOGITS
     Minang
    1.83
     bandung
    1.78
     hcm
    1.77
     death
    1.74
     stockholm
    1.73
     wien
    1.73
     increa
    1.72
     Death
    1.71
     Juf
    1.70
     jorge
    1.67
    Activations Density 0.099%

    No Known Activations