© 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. 3128
    Prev
    Next
    INDEX
    Explanations

    phrases and statements emphasizing clarity or clarity of messages

    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
    50
    +0.25
    1.4%
    1839
    +0.12
    0.7%
    251
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1839
    +0.25
    0.04
    1435
    +0.12
    0.04
    1506
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.55
    
    -0.94
     intersper
    -0.86
     gratify
    -0.80
    /***
    -0.72
     endow
    -0.72
     endeav
    -0.69
    <?
    -0.68
     endeavouring
    -0.67
     amass
    -0.66
    POSITIVE LOGITS
     clear
    1.08
     Clear
    1.03
    clear
    1.00
    Clear
    0.98
     CLEAR
    0.96
    CLEAR
    0.89
     clearer
    0.84
     clarity
    0.82
     clears
    0.76
     Clearing
    0.74
    Activations Density 0.076%

    No Known Activations