Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2886
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial medical practices and ethical debates

    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
    110
    +0.10
    0.3%
    207
    +0.09
    0.3%
    1843
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    207
    +0.10
    0.04
    110
    +0.09
    0.03
    509
    +0.08
    0.04
    Negative Logits
     depic
    -1.74
     affor
    -1.68
     unden
    -1.68
     impra
    -1.68
     guarante
    -1.65
     Mlle
    -1.64
     increa
    -1.61
     indestru
    -1.60
     emphat
    -1.60
     accla
    -1.59
    POSITIVE LOGITS
     Hospice
    0.86
     death
    0.80
     dying
    0.76
     hospice
    0.73
    death
    0.69
     terminal
    0.69
     EoL
    0.67
     die
    0.65
     Funeral
    0.65
     deaths
    0.65
    Activations Density 0.305%

    No Known Activations