© 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. 2129
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and hospitals

    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
    203
    +0.12
    0.4%
    555
    +0.11
    0.4%
    1870
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.03
    555
    +0.11
    0.02
    976
    +0.11
    0.02
    Negative Logits
     disreg
    -1.12
     intermitt
    -1.11
     scrat
    -1.06
     suscep
    -1.01
     impra
    -0.98
     increa
    -0.96
     cushi
    -0.96
     funko
    -0.94
     intersper
    -0.94
     guarante
    -0.93
    POSITIVE LOGITS
     hospital
    1.33
     Hospital
    1.26
    Hospital
    1.22
    hospital
    1.19
     hospitals
    1.15
     Hospitals
    0.99
     HOSPITAL
    0.96
    Hospitals
    0.93
    OSPITAL
    0.86
     hospitalized
    0.78
    Activations Density 0.066%

    No Known Activations