© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3713
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to individuals' actions or statements

    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
    50
    +0.34
    1.5%
    381
    +0.13
    0.6%
    1510
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.34
    0.10
    1510
    +0.13
    0.07
    1637
    +0.11
    0.08
    Negative Logits
    <bos>
    -2.49
     fluo
    -0.94
     intersper
    -0.92
     nutella
    -0.92
     aquarelle
    -0.89
     bordeaux
    -0.87
     oleo
    -0.85
     Adieu
    -0.84
     parma
    -0.83
     crê
    -0.82
    POSITIVE LOGITS
     heapq
    0.85
    He
    0.76
    bufio
    0.72
    Sklici
    0.71
     He
    0.70
    .='
    0.69
    =="")
    0.69
    She
    0.67
    They
    0.66
    ==""){
    0.66
    Activations Density 0.331%

    No Known Activations