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. 15950
    Prev
    Next
    INDEX
    Explanations

    references to overcoming physical challenges and defying medical advice

    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
    764
    +0.36
    1.3%
    1150
    +0.12
    0.4%
    332
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.36
    0.07
    509
    +0.12
    0.05
    74
    +0.10
    0.02
    Negative Logits
    ніципалі
    -0.70
     Bourgoin
    -0.69
     palab
    -0.67
     glan
    -0.66
    <bos>
    -0.65
     otomatig
    -0.63
    Obrázky
    -0.63
     Paglinawan
    -0.63
     estekak
    -0.62
     تضيفلها
    -0.61
    POSITIVE LOGITS
     Whence
    0.95
     Wtf
    0.92
     pamph
    0.90
     Wherefore
    0.86
     unspeak
    0.83
     McLaugh
    0.82
     Vaugh
    0.82
     McInt
    0.82
     Lmao
    0.81
     Ename
    0.81
    Activations Density 0.544%

    No Known Activations