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. 8309
    Prev
    Next
    INDEX
    Explanations

    information related to historical acts or legislative provisions related to education, specifically higher education and segregation

    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
    1253
    +0.12
    0.4%
    227
    +0.11
    0.3%
    939
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.07
    1336
    +0.11
    0.05
    919
    +0.08
    0.01
    Negative Logits
     fluo
    -0.73
     foon
    -0.68
     macrop
    -0.68
     juft
    -0.68
     ftre
    -0.67
     juf
    -0.65
     uncin
    -0.65
     bieber
    -0.65
     paff
    -0.65
     laft
    -0.64
    POSITIVE LOGITS
     universities
    0.89
     colleges
    0.87
     campuses
    0.86
     university
    0.78
     Colleges
    0.74
     tuition
    0.71
     college
    0.71
     Universities
    0.69
     campus
    0.69
     graduates
    0.69
    Activations Density 0.630%

    No Known Activations