© 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. 2751
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocacy and leadership in various organizational contexts

    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
    506
    +0.09
    0.3%
    50
    +0.07
    0.3%
    1044
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    875
    +0.09
    0.02
    1451
    +0.07
    0.02
    1082
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.91
    public
    -0.59
    ૌ
    -0.59
    ണ്ട
    -0.56
    typedef
    -0.55
    招
    -0.54
    void
    -0.53
    circ
    -0.53
    ोंने
    -0.53
    AddTagHelper
    -0.52
    POSITIVE LOGITS
     advocate
    1.98
     advocacy
    1.89
     advocates
    1.86
    advoc
    1.77
    Advoc
    1.77
     advoc
    1.76
     Advocates
    1.72
     Advocate
    1.69
     Advoc
    1.68
     Advocacy
    1.62
    Activations Density 0.086%

    No Known Activations