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. 13648
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to entropy and resistance in physics or computer science

    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
    1937
    +0.17
    0.8%
    662
    +0.17
    0.8%
    1276
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.17
    0.05
    1624
    +0.17
    0.04
    1276
    +0.16
    0.04
    Negative Logits
     Fus
    -0.52
     Fid
    -0.51
     Nug
    -0.51
     Kuj
    -0.51
     Thacker
    -0.51
     Eug
    -0.51
     Kark
    -0.51
     Ather
    -0.50
     Ror
    -0.50
     Maurer
    -0.50
    POSITIVE LOGITS
     ${\
    0.63
     abbraccio
    0.58
     sab
    0.57
    oarece
    0.56
     autunno
    0.55
    ${\
    0.55
    Sab
    0.55
     Sab
    0.55
    /*
    0.54
     Tribe
    0.54
    Activations Density 0.334%

    No Known Activations