© 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. 2152
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of sensors

    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
    1870
    +0.15
    0.6%
    1047
    +0.14
    0.6%
    950
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1047
    +0.15
    0.02
    950
    +0.14
    0.02
    1624
    +0.14
    0.02
    Negative Logits
    otheby
    -0.52
    iddhar
    -0.49
     Esco
    -0.49
     Raoul
    -0.48
    +#+#
    -0.47
    criptures
    -0.47
    cdon
    -0.46
    DotNetBar
    -0.46
     Yal
    -0.45
     Schrö
    -0.45
    POSITIVE LOGITS
     sensor
    1.37
     sensors
    1.30
     Sensor
    1.29
    Sensor
    1.18
    sensor
    1.16
     Sensors
    1.15
    Sensors
    1.07
     SENSOR
    1.03
     sensores
    0.99
    sensors
    0.96
    Activations Density 0.095%

    No Known Activations