Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15978
    Prev
    Next
    INDEX
    Explanations

    dates and time-related information

    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
    1343
    +0.12
    0.4%
    1978
    +0.10
    0.3%
    1023
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.12
    0.04
    321
    +0.10
    0.04
    1614
    +0.09
    0.04
    Negative Logits
    scalatest
    -0.49
    Geral
    -0.43
     Pardo
    -0.43
    Cyfeiriadau
    -0.43
     bleef
    -0.43
    Beskrivning
    -0.43
     earnestness
    -0.43
     feveral
    -0.43
    はじめに
    -0.41
     moft
    -0.41
    POSITIVE LOGITS
     accol
    0.56
    🥲
    0.55
     soggior
    0.55
     quí
    0.53
     recensione
    0.53
     ristor
    0.52
     vasi
    0.52
    ouches
    0.51
    <?
    0.51
     chiunque
    0.50
    Activations Density 0.097%

    No Known Activations