© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3605
    Prev
    Next
    INDEX
    Explanations

    mentions of fats in the context of physical health and body image

    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
    1328
    +0.19
    0.8%
    1387
    +0.16
    0.6%
    680
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1387
    +0.19
    0.03
    1328
    +0.16
    0.02
    680
    +0.15
    0.02
    Negative Logits
     endeavouring
    -0.61
     cushi
    -0.60
     melange
    -0.60
     Assorted
    -0.59
     nmax
    -0.58
     rval
    -0.57
     vainly
    -0.56
     Stretcher
    -0.56
     unspeak
    -0.56
     loveliness
    -0.55
    POSITIVE LOGITS
     fat
    1.32
    fat
    1.29
     Fat
    1.28
    Fat
    1.28
    FAT
    1.08
     FAT
    1.07
     fats
    0.94
     fatty
    0.77
     Fats
    0.72
     grasa
    0.71
    Activations Density 0.087%

    No Known Activations