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. 1394
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming and technology

    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
    573
    +0.07
    0.2%
    1651
    +0.07
    0.2%
    394
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.07
    0.05
    1648
    +0.07
    0.02
    1446
    +0.07
    0.03
    Negative Logits
     aen
    -0.99
     fta
    -0.98
     thut
    -0.98
     erec
    -0.95
     Juf
    -0.94
     yong
    -0.93
     huma
    -0.93
     lein
    -0.92
     miu
    -0.91
     wien
    -0.90
    POSITIVE LOGITS
     occurs
    0.62
     done
    0.59
    ⓧ
    0.59
    arrol
    0.58
     occurred
    0.55
     conducted
    0.55
    HasColumnName
    0.55
     provided
    0.54
     undertaken
    0.54
     performed
    0.54
    Activations Density 0.307%

    No Known Activations