© 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. 13262
    Prev
    Next
    INDEX
    Explanations

    references to sensations and feelings, specifically related to pain and tingling

    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
    906
    +0.10
    0.3%
    509
    +0.10
    0.3%
    1519
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.10
    0.06
    736
    +0.10
    0.05
    1267
    +0.08
    0.04
    Negative Logits
     haup
    -1.28
     jorge
    -1.25
     alberto
    -1.24
     sergio
    -1.24
     accla
    -1.23
     wien
    -1.22
     ivi
    -1.21
     daf
    -1.20
     socie
    -1.20
     napoli
    -1.19
    POSITIVE LOGITS
     feeling
    0.82
     felt
    0.82
     feel
    0.78
     sensation
    0.68
     feels
    0.68
     відчу
    0.61
    feeling
    0.60
    feel
    0.58
     sensations
    0.55
     Feel
    0.55
    Activations Density 0.356%

    No Known Activations