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. 8317
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology integration and implementation

    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
    1233
    +0.17
    0.6%
    120
    +0.14
    0.5%
    537
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.17
    0.03
    120
    +0.14
    0.03
    1573
    +0.14
    0.02
    Negative Logits
     ciasc
    -0.51
    Inoltre
    -0.50
    postolic
    -0.47
     basan
    -0.47
    nanoTime
    -0.45
     habet
    -0.45
     clim
    -0.45
     locom
    -0.45
     tachy
    -0.44
    msgSender
    -0.44
    POSITIVE LOGITS
     integrate
    1.09
     integration
    1.07
     Integrate
    1.06
     Integration
    1.05
    Integr
    1.05
     integrations
    1.04
    integr
    1.00
     integrated
    0.99
    integrated
    0.99
    integrate
    0.99
    Activations Density 0.101%

    No Known Activations