© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7140
    Prev
    Next
    INDEX
    Explanations

    phrases related to close personal relationships

    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
    544
    +0.12
    0.4%
    650
    +0.11
    0.4%
    1222
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    650
    +0.12
    0.04
    1222
    +0.11
    0.04
    900
    +0.11
    0.04
    Negative Logits
     Châ
    -0.50
     perpétu
    -0.47
     sév
    -0.46
    jRadioButton
    -0.45
     Bege
    -0.45
    typeparam
    -0.44
     coiff
    -0.43
    ütün
    -0.43
    aVar
    -0.43
     Souha
    -0.42
    POSITIVE LOGITS
     close
    1.17
     Close
    1.11
    close
    1.07
    Close
    1.06
     CLOSE
    1.04
    CLOSE
    0.97
     closer
    0.88
     closeness
    0.86
     clos
    0.85
     closes
    0.84
    Activations Density 0.099%

    No Known Activations