© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10676
    Prev
    Next
    INDEX
    Explanations

    information related to tourism and travel experiences

    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
    738
    +0.09
    0.3%
    1013
    +0.08
    0.2%
    455
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1441
    +0.09
    0.04
    1031
    +0.08
    0.04
    415
    +0.08
    0.03
    Negative Logits
     ordina
    -0.75
     territo
    -0.70
     umo
    -0.69
     sena
    -0.67
     brille
    -0.67
     automatica
    -0.65
     espres
    -0.64
     karo
    -0.63
     diabe
    -0.63
     assiste
    -0.63
    POSITIVE LOGITS
     travel
    0.89
     vacations
    0.80
     vacation
    0.79
     trip
    0.79
     itinerary
    0.78
     travelling
    0.72
     trips
    0.71
     tourist
    0.71
     traveling
    0.70
     itineraries
    0.70
    Activations Density 0.814%

    No Known Activations