© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1901
    Prev
    Next
    INDEX
    Explanations

    references to the company "Wal-Mart"

    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
    347
    +0.16
    0.6%
    687
    +0.12
    0.5%
    1127
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.16
    0.02
    1895
    +0.12
    0.02
    1127
    +0.12
    0.02
    Negative Logits
     muna
    -0.63
     guma
    -0.59
     habang
    -0.51
     kapag
    -0.50
     buhay
    -0.47
     ngayon
    -0.46
     Topeka
    -0.46
     kahit
    -0.45
     makita
    -0.45
     bago
    -0.45
    POSITIVE LOGITS
     Wal
    1.56
    Wal
    1.52
     WAL
    1.35
     wal
    1.23
    WAL
    1.20
    wal
    1.08
     Walton
    1.02
     Walters
    1.00
     Walden
    0.98
     Wally
    0.97
    Activations Density 0.088%

    No Known Activations