© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4413
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named Dale, with variations in text formatting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    120
    +0.18
    0.8%
    1573
    +0.16
    0.7%
    795
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.18
    0.03
    981
    +0.16
    0.04
    1092
    +0.14
    0.03
    Negative Logits
     sienta
    -0.58
     tramonto
    -0.53
     giù
    -0.51
     ovunque
    -0.50
     accanto
    -0.48
    Trichlor
    -0.47
     nekaj
    -0.47
    Consigli
    -0.46
    mistry
    -0.46
    conut
    -0.46
    POSITIVE LOGITS
     Ale
    0.98
    Ale
    0.97
     ALE
    0.96
     Dale
    0.94
    Dale
    0.92
    ale
    0.92
     dale
    0.91
    ALE
    0.91
     ale
    0.87
     Hale
    0.86
    Activations Density 0.187%

    No Known Activations