© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2511
    Prev
    Next
    INDEX
    Explanations

    references to the name "Jesse."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    812
    +0.25
    1.4%
    314
    +0.15
    0.8%
    241
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    812
    +0.25
    0.03
    1575
    +0.15
    0.02
    1097
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.05
    OGND
    -0.66
    zydent
    -0.61
     platform
    -0.60
    platform
    -0.59
    RTLR
    -0.59
    RTEX
    -0.59
    addCriterion
    -0.59
    webElementXpaths
    -0.57
    
    -0.56
    POSITIVE LOGITS
     Jesse
    1.56
    Jesse
    1.51
     JES
    1.15
     socie
    1.08
     Luxem
    1.00
     fei
    0.96
     gesta
    0.94
     noel
    0.93
     jor
    0.93
     franz
    0.93
    Activations Density 0.170%

    No Known Activations