© 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. 3681
    Prev
    Next
    INDEX
    Explanations

    names associated with historical figures and audiences in political 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
    1842
    +0.15
    0.5%
    50
    +0.13
    0.4%
    1741
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.15
    0.06
    138
    +0.13
    0.07
    1741
    +0.11
    0.01
    Negative Logits
    <bos>
    -2.10
    Více
    -0.81
    ⓧ
    -0.80
    Vlastnosti
    -0.79
    loài
    -0.77
    <!--
    -0.75
    <?
    -0.73
    Díky
    -0.72
    
    -0.70
    Preço
    -0.69
    POSITIVE LOGITS
     increa
    1.83
     maneu
    1.80
     stockholm
    1.71
     impra
    1.66
     strick
    1.55
     affor
    1.53
     attemp
    1.50
     thut
    1.49
     eiffel
    1.48
     snoopy
    1.47
    Activations Density 0.726%

    No Known Activations