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. 15940
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and global issues, focusing on solutions and prevention

    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
    764
    +0.18
    0.6%
    1253
    +0.09
    0.3%
    1533
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.18
    0.06
    64
    +0.09
    0.04
    488
    +0.07
    0.06
    Negative Logits
     ftu
    -0.85
     fup
    -0.79
     fep
    -0.79
     fta
    -0.79
     »>
    -0.78
    «<
    -0.77
    !!</
    -0.73
     applau
    -0.70
     !...
    -0.70
     perfon
    -0.70
    POSITIVE LOGITS
     improve
    0.63
     betterment
    0.62
     healthier
    0.62
     sustainable
    0.61
     solve
    0.60
     achieve
    0.60
     better
    0.60
     improvement
    0.59
     sustainably
    0.59
    BeforeAll
    0.58
    Activations Density 0.579%

    No Known Activations