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. 1771
    Prev
    Next
    INDEX
    Explanations

    references to Puerto Rico and related terms

    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
    1334
    +0.14
    0.7%
    169
    +0.13
    0.6%
    381
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.04
    678
    +0.13
    0.04
    1056
    +0.13
    0.03
    Negative Logits
     disreg
    -0.93
     vainly
    -0.89
     roused
    -0.88
     impelled
    -0.86
     dumbass
    -0.82
    /**
    -0.79
     ardour
    -0.77
     endeavored
    -0.76
     endeavouring
    -0.75
     strolled
    -0.75
    POSITIVE LOGITS
     konserv
    1.05
     Kategor
    1.03
     kooper
    0.99
     silikon
    0.99
     kosme
    0.98
     akus
    0.97
     keramik
    0.95
     Strukt
    0.94
     alkoh
    0.93
     maksi
    0.93
    Activations Density 0.202%

    No Known Activations