© 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. 3998
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or suggestions regarding potential actions

    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
    +0.26
    1.0%
    381
    +0.14
    0.6%
    1103
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1264
    +0.26
    0.05
    537
    +0.14
    0.05
    1505
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.04
    endwhile
    -0.62
    }]
    -0.61
     endwhile
    -0.57
     unify
    -0.56
    }],
    -0.55
    BufferedWriter
    -0.54
    Πηγές
    -0.53
    SizeMode
    -0.53
    Таким
    -0.53
    POSITIVE LOGITS
     🤣🤣
    1.00
     tupperware
    0.97
     milf
    0.97
     gilet
    0.94
     hoody
    0.90
     desir
    0.90
     pollut
    0.90
     😩
    0.89
     😭😭
    0.89
     🥲
    0.88
    Activations Density 0.303%

    No Known Activations