© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 206
    Prev
    Next
    INDEX
    Explanations

    mentions of tollbooths

    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
    410
    +0.12
    0.4%
    1350
    +0.10
    0.3%
    241
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.12
    0.02
    1495
    +0.10
    0.02
    1778
    +0.09
    0.02
    Negative Logits
    <tr>
    -0.74
    /**
    -0.73
    立
    -0.73
    namespace
    -0.72
    //
    -0.72
    */
    -0.72
    tie
    -0.70
    /*
    -0.70
    WriteLiteral
    -0.70
    max
    -0.69
    POSITIVE LOGITS
     toll
    3.03
     Toll
    2.86
    Toll
    2.62
     tolls
    2.46
    toll
    2.43
     strick
    2.11
     affor
    2.10
     stockholm
    2.07
     maneu
    2.03
     increa
    2.03
    Activations Density 0.191%

    No Known Activations