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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1171
    Prev
    Next
    INDEX
    Explanations

    mentions of "resolution" or related contextual terms regarding formal agreements or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.22
    1.4%
    313
    +0.14
    0.9%
    1328
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1065
    +0.22
    0.02
    313
    +0.14
    0.02
    892
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.65
    InjectMocks
    -0.72
    /***
    
    -0.71
    ///**
    -0.70
     promul
    -0.61
     lighten
    -0.58
    /**
    -0.56
     reinstate
    -0.56
     reunite
    -0.55
     amass
    -0.54
    POSITIVE LOGITS
     resolution
    1.24
     resolutions
    1.17
     Resolution
    1.15
     Resolutions
    1.10
    resolution
    1.06
     RESOLUTION
    1.04
    Resolution
    1.04
     Resolved
    0.98
     resolu
    0.95
     Resolver
    0.94
    Activations Density 0.041%

    No Known Activations