© 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. 4144
    Prev
    Next
    INDEX
    Explanations

    instances of the word "after" followed by a number indicating a time period

    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
    1023
    +0.17
    0.6%
    1993
    +0.14
    0.5%
    596
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1023
    +0.17
    0.10
    1993
    +0.14
    0.10
    596
    +0.13
    0.07
    Negative Logits
     pymysql
    -0.52
    testify
    -0.49
    RLock
    -0.47
     bağlantılar
    -0.46
    Ken
    -0.45
    ländische
    -0.45
    jsoup
    -0.44
    CURSO
    -0.43
    bcryptjs
    -0.43
    industria
    -0.42
    POSITIVE LOGITS
     fter
    1.01
     felicità
    0.89
     voleva
    0.86
     AFTER
    0.82
     viciss
    0.81
     Ikan
    0.81
    andafter
    0.80
     coscienza
    0.79
     seksi
    0.79
     soigne
    0.78
    Activations Density 0.173%

    No Known Activations