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. 1040
    Prev
    Next
    INDEX
    Explanations

    instances of the word "burst" and its variations, indicating intense or dramatic actions

    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
    +0.16
    0.8%
    204
    +0.13
    0.7%
    690
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.16
    0.03
    690
    +0.13
    0.02
    1416
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.38
    Хо
    -0.81
    المناصب
    -0.73
     հղումներ
    -0.72
    mail
    -0.71
    RegressionTest
    -0.71
    BUYER
    -0.71
    Vegeu
    -0.70
    ValueGenerated
    -0.70
    KURZBESCHREIBUNG
    -0.70
    POSITIVE LOGITS
     increa
    2.28
     emphat
    2.26
     maneu
    2.25
     disagre
    2.24
     impra
    2.22
     reluct
    2.22
     thut
    2.20
     affor
    2.18
     accla
    2.15
     fta
    2.14
    Activations Density 0.093%

    No Known Activations