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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8047
    Prev
    Next
    INDEX
    Explanations

    information related to woodworking techniques and products

    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
    1385
    +0.16
    0.5%
    1150
    +0.14
    0.4%
    876
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.16
    0.06
    1385
    +0.14
    0.04
    2044
    +0.12
    0.05
    Negative Logits
     praktik
    -1.04
     meras
    -0.94
     interro
    -0.89
     kön
    -0.89
     revan
    -0.87
     miniatura
    -0.87
     Jerusal
    -0.86
     kompati
    -0.86
     alkoh
    -0.86
     geograf
    -0.84
    POSITIVE LOGITS
     coating
    0.69
     coatings
    0.65
     człowie
    0.62
     marié
    0.60
     coat
    0.59
     finish
    0.57
     wiecz
    0.56
     coats
    0.56
     Coating
    0.55
     surface
    0.55
    Activations Density 0.327%

    No Known Activations