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. 1039
    Prev
    Next
    INDEX
    Explanations

    terms related to demographic and political divisions, particularly involving majorities and minorities

    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
    +0.20
    0.7%
    1385
    +0.16
    0.6%
    198
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.20
    0.09
    198
    +0.16
    0.07
    468
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.14
     finally
    -0.65
     went
    -0.62
     put
    -0.62
     reik
    -0.61
     had
    -0.61
     brought
    -0.60
     bring
    -0.59
     was
    -0.58
     came
    -0.58
    POSITIVE LOGITS
     Juf
    1.35
     hcm
    1.34
     bandung
    1.30
     jaya
    1.27
     prét
    1.25
     shopee
    1.24
     Minang
    1.24
     Karang
    1.24
     prétend
    1.24
     dises
    1.24
    Activations Density 0.406%

    No Known Activations