© 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. 2618
    Prev
    Next
    INDEX
    Explanations

    the word "habit" in various contexts related to behavior or routines

    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
    1624
    +0.09
    0.3%
    1331
    +0.08
    0.2%
    966
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1095
    +0.09
    0.02
    1866
    +0.08
    0.02
    256
    +0.07
    0.02
    Negative Logits
    /***
    -0.65
    displayquote
    -0.61
    ittoria
    -0.57
    await
    -0.55
    <tfoot>
    -0.55
     insertar
    -0.53
    /*++
    -0.51
    getClassLoader
    -0.50
    itigation
    -0.49
    ComponentModel
    -0.49
    POSITIVE LOGITS
     habit
    3.20
     Habit
    2.64
     habits
    2.43
     Habits
    2.23
    habit
    2.11
    Habit
    2.10
    habits
    1.67
     HAB
    1.63
     hábito
    1.60
     habitual
    1.38
    Activations Density 0.130%

    No Known Activations