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. 649
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "even" in various contexts

    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
    +0.28
    1.4%
    1482
    +0.13
    0.6%
    544
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1482
    +0.28
    0.06
    201
    +0.13
    0.05
    544
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.67
    ⓧ
    -0.72
    Vegeu
    -0.71
    <tfoot>
    -0.71
    /***
    
    -0.65
    Autoritní
    -0.60
    LinkedHashMap
    -0.60
    glMatrixMode
    -0.59
    mtable
    -0.59
    EndProject
    -0.57
    POSITIVE LOGITS
     maneu
    1.33
     hilux
    1.21
     tupperware
    1.21
     ecru
    1.20
     chrysler
    1.20
     pajero
    1.19
     mondeo
    1.16
     lamborghini
    1.14
     cabrio
    1.14
     lidl
    1.13
    Activations Density 0.060%

    No Known Activations