© 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. 2007
    Prev
    Next
    INDEX
    Explanations

    texts related to travel and leisure activities

    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
    2034
    +0.29
    0.9%
    2019
    +0.14
    0.5%
    1403
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.29
    0.05
    382
    +0.14
    0.06
    924
    +0.14
    0.06
    Negative Logits
     destul
    -0.70
    bonsoir
    -0.69
     ļoti
    -0.68
     nicio
    -0.66
     ytter
    -0.66
     nepiecieš
    -0.65
    ביוגרפיה
    -0.64
    /**
    -0.64
    voici
    -0.64
     validamos
    -0.63
    POSITIVE LOGITS
     swarovski
    1.08
     tupperware
    1.03
     tiffany
    1.02
     edp
    1.02
     snoopy
    1.00
     lts
    0.96
     guarante
    0.95
     affor
    0.95
     lidl
    0.93
     peppa
    0.92
    Activations Density 0.401%

    No Known Activations