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. 10094
    Prev
    Next
    INDEX
    Explanations

    information related to a specific medical study involving GelPell® microgel CBD capsules and their effects on bioavailability and absorption

    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
    876
    +0.16
    0.5%
    752
    +0.10
    0.3%
    617
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.16
    0.05
    2002
    +0.10
    0.03
    1499
    +0.09
    0.05
    Negative Logits
     shenan
    -0.97
     Outre
    -0.96
     pamph
    -0.93
     Souha
    -0.93
     soudain
    -0.92
     bascul
    -0.91
     racon
    -0.90
     Toujours
    -0.88
     philanth
    -0.87
     vagu
    -0.86
    POSITIVE LOGITS
     absorbed
    0.55
    Bioaccumulative
    0.54
     absorption
    0.54
     cursus
    0.53
    cokinetics
    0.51
     absorb
    0.50
     Bioaccumulative
    0.50
     adsorption
    0.49
     levis
    0.49
     thụ
    0.48
    Activations Density 0.333%

    No Known Activations