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. 615
    Prev
    Next
    INDEX
    Explanations

    phrases related to police actions and protests

    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
    604
    +0.13
    0.4%
    946
    +0.12
    0.4%
    939
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.13
    0.07
    939
    +0.12
    0.06
    880
    +0.09
    0.05
    Negative Logits
     hairc
    -1.28
     ecru
    -1.27
     tricot
    -1.25
     peppa
    -1.14
     tupperware
    -1.11
     swarovski
    -1.09
     snoopy
    -1.07
     cushi
    -1.07
     bonbons
    -1.06
     amigurumi
    -1.04
    POSITIVE LOGITS
     protesters
    0.64
     crowd
    0.58
     police
    0.58
     peaceful
    0.55
     clashes
    0.55
     arrested
    0.55
     arrests
    0.55
     attendees
    0.52
    Police
    0.51
     peacefully
    0.51
    Activations Density 0.711%

    No Known Activations