© 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. 4573
    Prev
    Next
    INDEX
    Explanations

    the number "three"

    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
    776
    +0.20
    0.8%
    1937
    +0.16
    0.6%
    303
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.20
    0.06
    303
    +0.16
    0.05
    201
    +0.12
    0.03
    Negative Logits
     dizaines
    -0.65
     centaines
    -0.56
     necesar
    -0.56
    枚目
    -0.52
     milliers
    -0.52
     decembrie
    -0.49
     prochaines
    -0.48
     hommage
    -0.48
    FlatAppearance
    -0.48
     octombrie
    -0.47
    POSITIVE LOGITS
    three
    0.94
     Tiga
    0.86
     three
    0.82
     THREE
    0.80
    Three
    0.77
    THREE
    0.76
     Three
    0.76
     Trois
    0.68
     guma
    0.66
     Muhamma
    0.65
    Activations Density 0.106%

    No Known Activations