© 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. 2567
    Prev
    Next
    INDEX
    Explanations

    references to a person named Miller, potentially related to fraudulent or criminal activities

    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.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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    783
    +0.09
    0.3%
    2004
    +0.09
    0.3%
    950
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1548
    +0.09
    0.03
    950
    +0.09
    0.03
    2004
    +0.09
    0.03
    Negative Logits
    <bos>
    -1.31
     sit
    -0.77
    public
    -0.77
     put
    -0.75
    加
    -0.74
    .
    -0.73
    //
    -0.73
    ,
    -0.73
     fix
    -0.72
                
    -0.72
    POSITIVE LOGITS
     accla
    2.44
     miller
    2.38
     stockholm
    2.36
     affor
    2.35
     wien
    2.32
     inev
    2.32
     increa
    2.30
     effe
    2.30
     impra
    2.29
     strick
    2.26
    Activations Density 0.139%

    No Known Activations