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. 13657
    Prev
    Next
    INDEX
    Explanations

    statements related to laws, legal recommendations, and government appointments

    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
    872
    +0.19
    0.6%
    1499
    +0.09
    0.3%
    1297
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.19
    0.07
    1380
    +0.09
    0.03
    488
    +0.08
    0.06
    Negative Logits
     emphat
    -1.19
     depic
    -1.09
     hairc
    -1.07
     hentai
    -1.07
     desir
    -1.07
     guarante
    -1.06
     pixar
    -1.06
     nutella
    -1.05
     intersper
    -1.03
     hasbro
    -1.03
    POSITIVE LOGITS
     laws
    0.85
     rules
    0.78
     law
    0.73
     regulations
    0.73
    rules
    0.69
     rule
    0.66
     legislation
    0.66
     enforcement
    0.65
    laws
    0.62
     Rules
    0.61
    Activations Density 0.671%

    No Known Activations