© 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. 3364
    Prev
    Next
    INDEX
    Explanations

    variations of the word "retweet" in a social media context

    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
    +0.15
    0.9%
    1677
    +0.13
    0.8%
    1296
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1763
    +0.15
    0.02
    1233
    +0.13
    0.02
    1677
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.97
     intersper
    -0.99
    ⓧ
    -0.92
     hasbro
    -0.78
    <?
    -0.73
     endow
    -0.73
    /**
    -0.72
     situate
    -0.72
     infest
    -0.71
    
    -0.71
    POSITIVE LOGITS
     Ret
    1.28
    Ret
    1.22
     ret
    1.17
    ret
    1.10
     RET
    0.99
    RET
    0.97
     Retreat
    0.84
     retreat
    0.80
     retreats
    0.78
    retweet
    0.71
    Activations Density 0.056%

    No Known Activations