© 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. 4035
    Prev
    Next
    INDEX
    Explanations

    text related to emotional intelligence and behavioral understanding

    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
    1870
    +0.08
    0.2%
    924
    +0.08
    0.2%
    851
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.08
    0.04
    1265
    +0.08
    0.04
    1510
    +0.07
    0.04
    Negative Logits
     disagre
    -1.82
     reluct
    -1.72
     depic
    -1.66
     encomp
    -1.65
     apprehen
    -1.62
     increa
    -1.55
     gaily
    -1.53
     unspeak
    -1.52
     unwarran
    -1.50
     berea
    -1.45
    POSITIVE LOGITS
     سكانية
    0.68
    '&:
    0.62
    كتوبر
    0.61
    Xna
    0.61
    ांकि
    0.60
    رشف
    0.59
     Wirk
    0.58
    jercicios
    0.58
    Solución
    0.58
    льевич
    0.57
    Activations Density 0.403%

    No Known Activations