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. 645
    Prev
    Next
    INDEX
    Explanations

    references to religious and philosophical concepts alongside discussions of abortion and women's rights

    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
    +0.26
    1.1%
    394
    +0.18
    0.8%
    468
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.26
    0.09
    394
    +0.18
    0.14
    1856
    +0.09
    0.11
    Negative Logits
    <bos>
    -1.88
    ⓧ
    -0.65
    <?
    -0.57
    <blockquote>
    -0.56
    slf
    -0.56
    displayquote
    -0.56
    .
    -0.56
     engage
    -0.55
    enter
    -0.55
     earn
    -0.54
    POSITIVE LOGITS
     bandung
    1.54
     Juf
    1.44
     sovere
    1.39
     Minang
    1.39
     lele
    1.35
     unwarran
    1.31
     Banjar
    1.30
     quoc
    1.29
     Intere
    1.25
     surabaya
    1.24
    Activations Density 2.723%

    No Known Activations