© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1481
    Prev
    Next
    INDEX
    Explanations

    mentions of time-related phrases, particularly those involving days

    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
    +0.27
    1.5%
    1023
    +0.12
    0.6%
    1671
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2004
    +0.27
    0.04
    1023
    +0.12
    0.04
    147
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.95
    },{
    
    -0.71
    Билгалдахарш
    -0.67
    lateinit
    -0.63
    ineno
    -0.63
    IContainer
    -0.62
    init
    -0.61
    DataMember
    -0.60
    ɵɵ
    -0.60
    ///**
    -0.59
    POSITIVE LOGITS
     unwarran
    1.76
     maneu
    1.69
     fays
    1.66
     disagre
    1.65
     ftu
    1.62
     unlaw
    1.62
     impractica
    1.61
     perfon
    1.60
     increa
    1.57
     madonna
    1.57
    Activations Density 0.093%

    No Known Activations