© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4245
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making and consideration of options

    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
    80
    +0.09
    0.3%
    678
    +0.09
    0.3%
    597
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    860
    +0.09
    0.04
    223
    +0.09
    0.03
    240
    +0.08
    0.03
    Negative Logits
     Pourtant
    -0.61
     gucci
    -0.55
     suscep
    -0.54
     elena
    -0.53
     disreg
    -0.53
     accla
    -0.53
     inconce
    -0.52
     catast
    -0.51
     emphat
    -0.50
     resul
    -0.49
    POSITIVE LOGITS
     possibilities
    0.78
     possibility
    0.77
     options
    0.76
    possibility
    0.66
     option
    0.64
     alternatives
    0.64
     Options
    0.63
     posibilidad
    0.62
     Option
    0.61
     ways
    0.59
    Activations Density 0.367%

    No Known Activations