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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4586
    Prev
    Next
    INDEX
    Explanations

    references to the name "Philip."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    687
    +0.21
    1.2%
    50
    +0.14
    0.9%
    168
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    687
    +0.21
    0.03
    168
    +0.14
    0.03
    241
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.29
    
    -0.75
     inaugurate
    -0.62
    ുറ
    -0.59
    ⓧ
    -0.58
     enjoined
    -0.56
     liberate
    -0.56
     unlock
    -0.54
     eradicate
    -0.54
     mobilize
    -0.52
    POSITIVE LOGITS
     Philip
    1.47
    Philip
    1.43
     PHILIP
    1.23
     Phillip
    1.22
    Phillip
    1.16
     philipp
    1.11
     phi
    1.02
     zyn
    0.98
     philips
    0.96
     PHIL
    0.95
    Activations Density 0.038%

    No Known Activations