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. 749
    Prev
    Next
    INDEX
    Explanations

    website URLs

    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
    2034
    +0.15
    0.5%
    1343
    +0.13
    0.4%
    924
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.15
    0.04
    24
    +0.13
    0.03
    992
    +0.12
    0.03
    Negative Logits
    toHaveBeen
    -0.59
     faudrait
    -0.57
    noticia
    -0.56
     constate
    -0.55
    carboxylic
    -0.55
    aurait
    -0.54
    Peut
    -0.53
    Sábado
    -0.53
    Parabéns
    -0.53
    boîte
    -0.52
    POSITIVE LOGITS
    <bos>
    0.69
     saluti
    0.64
    {?>
    0.63
     HIL
    0.63
     ////
    0.62
     contex
    0.62
     scom
    0.62
     erad
    0.61
     HED
    0.60
     NIOS
    0.59
    Activations Density 0.048%

    No Known Activations