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. 836
    Prev
    Next
    INDEX
    Explanations

    discount offers and promotional deals related to retail products

    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
    +0.31
    1.2%
    1403
    +0.14
    0.5%
    1177
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1403
    +0.31
    0.03
    1876
    +0.14
    0.03
    924
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.43
    afterEach
    -0.74
    DeleteMapping
    -0.72
     NSCoder
    -0.71
    //});
    -0.71
    PutMapping
    -0.70
    VIAF
    -0.68
    lateinit
    -0.68
    //}
    
    -0.68
    addPreferredGap
    -0.67
    POSITIVE LOGITS
     maneu
    1.45
     scrat
    1.44
     accla
    1.41
     jurassic
    1.41
     shenan
    1.41
     resear
    1.39
     reluct
    1.36
     impra
    1.34
     snoopy
    1.33
     hairc
    1.30
    Activations Density 0.311%

    No Known Activations