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. 6856
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and mental health issues

    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
    +0.30
    1.2%
    752
    +0.14
    0.5%
    468
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.30
    0.04
    468
    +0.14
    0.03
    955
    +0.14
    0.03
    Negative Logits
    <bos>
    -2.91
     Paglinawan
    -0.79
    errHandler
    -0.76
    ,
    -0.74
    往
    -0.74
    isContained
    -0.74
    octanol
    -0.73
    /*---
    -0.73
    Geplaatst
    -0.73
     mxArray
    -0.73
    POSITIVE LOGITS
     sovere
    2.22
     Juf
    2.20
     fta
    2.17
     stockholm
    2.15
     hcm
    2.10
     affor
    2.09
     Confu
    2.05
     increa
    2.04
     secon
    2.00
     milf
    1.99
    Activations Density 0.262%

    No Known Activations