© 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 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. 5853
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interactions and emotional intelligence, focusing on understanding and interpreting the behaviors and motives of others

    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
    856
    +0.08
    0.2%
    1861
    +0.07
    0.2%
    1978
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1235
    +0.08
    0.07
    1485
    +0.07
    0.04
    908
    +0.07
    0.04
    Negative Logits
     diu
    -0.46
     kasarigan
    -0.45
     corrom
    -0.44
     pravi
    -0.44
    Jornal
    -0.43
     NTIS
    -0.43
    asteroide
    -0.43
     desapar
    -0.43
    Життєпис
    -0.43
    Ļ
    -0.43
    POSITIVE LOGITS
    trui
    0.69
     whom
    0.60
     تضيفلها
    0.59
     חיצוניים
    0.57
    bewerken
    0.57
    AndEndTag
    0.56
    whom
    0.56
     sportback
    0.55
     popoli
    0.55
     jetta
    0.51
    Activations Density 0.516%

    No Known Activations