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. 8378
    Prev
    Next
    INDEX
    Explanations

    information related to sports and athlete activities at a detailed level such as game details, player profiles, and achievements

    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
    1577
    +0.37
    1.5%
    1842
    +0.27
    1.1%
    599
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.37
    0.24
    1842
    +0.27
    0.15
    184
    +0.17
    0.02
    Negative Logits
     McLaugh
    -0.88
     Wtf
    -0.82
     unspeak
    -0.82
     Whence
    -0.80
     Daven
    -0.78
     withal
    -0.76
     Vaugh
    -0.75
     tolerably
    -0.73
     indescri
    -0.73
     impelled
    -0.73
    POSITIVE LOGITS
     Paglinawan
    0.76
     Meksiku
    0.72
     betweenstory
    0.67
     Rumuni
    0.65
    ніципа
    0.63
    Panamoan
    0.62
     manuten
    0.61
    cyklopedia
    0.60
    principalColumn
    0.60
    astéroïdes
    0.57
    Activations Density 8.271%

    No Known Activations