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. 13577
    Prev
    Next
    INDEX
    Explanations

    locations and titles related to key events

    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
    +0.28
    0.9%
    1343
    +0.24
    0.8%
    1842
    +0.24
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.28
    0.10
    856
    +0.24
    0.08
    1343
    +0.24
    0.10
    Negative Logits
     disagre
    -0.94
     Shakspeare
    -0.93
     unwarran
    -0.89
     unlaw
    -0.84
     reluct
    -0.82
     tolerably
    -0.82
     shenan
    -0.82
     Daven
    -0.82
     withal
    -0.81
     strick
    -0.80
    POSITIVE LOGITS
    {}
    
    0.63
     للمعارف
    0.53
     fono
    0.50
     שוליים
    0.48
     mej
    0.47
    fromCharCode
    0.47
     peniten
    0.46
    "}")
    0.46
     gela
    0.46
    fycat
    0.45
    Activations Density 1.779%

    No Known Activations