© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2659
    Prev
    Next
    INDEX
    Explanations

    the name "Dor" in various contexts

    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
    1053
    +0.17
    1.0%
    395
    +0.15
    0.9%
    990
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.17
    0.02
    227
    +0.15
    0.03
    990
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.56
    ⓧ
    -0.69
    /**
    -0.68
     Roskov
    -0.62
    <?
    -0.62
    
    -0.58
    Abitanti
    -0.58
    elemField
    -0.58
    cart
    -0.56
    context
    -0.55
    POSITIVE LOGITS
     Dor
    1.62
    Dor
    1.46
     dora
    1.29
     meis
    1.28
     DOR
    1.25
     saar
    1.15
     dor
    1.14
     increa
    1.13
     affor
    1.13
     inev
    1.13
    Activations Density 0.160%

    No Known Activations