© 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. 4303
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and their associated sentiments

    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
    +0.21
    0.8%
    1842
    +0.12
    0.4%
    198
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.21
    0.07
    2012
    +0.12
    0.06
    1055
    +0.11
    0.06
    Negative Logits
    <bos>
    -2.85
    ,
    -0.91
     is
    -0.90
      
    -0.88
    ，
    -0.87
     was
    -0.87
    .
    -0.86
     continue
    -0.84
    。
    -0.84
     and
    -0.83
    POSITIVE LOGITS
     increa
    2.84
     stockholm
    2.84
     affor
    2.83
     guarante
    2.76
     lamborghini
    2.73
     wherea
    2.66
     maneu
    2.65
     unlaw
    2.64
     lidl
    2.63
     accla
    2.61
    Activations Density 0.581%

    No Known Activations