© 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. 7395
    Prev
    Next
    INDEX
    Explanations

    references to competitive gaming events and players

    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
    227
    +0.14
    0.4%
    304
    +0.14
    0.4%
    690
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1551
    +0.14
    0.06
    81
    +0.14
    0.03
    455
    +0.11
    0.02
    Negative Logits
     desertcart
    -0.66
    hysema
    -0.65
     autorytatywna
    -0.64
     vacanza
    -0.63
     hectáreas
    -0.62
     <<<<<<<<<<<<<<
    -0.61
    oneofs
    -0.58
     salic
    -0.58
     dormitorios
    -0.58
    entistas
    -0.58
    POSITIVE LOGITS
     reluct
    1.97
     apprehen
    1.97
     accla
    1.92
     unspeak
    1.89
     intersper
    1.86
     impra
    1.86
     depic
    1.85
     emphat
    1.82
     shenan
    1.80
     philanth
    1.77
    Activations Density 0.581%

    No Known Activations