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. 1772
    Prev
    Next
    INDEX
    Explanations

    references to existential questions and the importance of individual experiences

    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
    +0.25
    0.9%
    297
    +0.10
    0.4%
    1406
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1369
    +0.25
    0.04
    46
    +0.10
    0.04
    1406
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.44
    devServer
    -0.69
    Tuy
    -0.66
    ApiProperty
    -0.66
    İstinadlar
    -0.66
    InputTagHelper
    -0.63
    jsxFileName
    -0.63
    Ikus
    -0.63
    FXML
    -0.62
    ⓧ
    -0.62
    POSITIVE LOGITS
     maneu
    1.50
     guarante
    1.48
     increa
    1.48
     accla
    1.47
     impra
    1.46
     riviera
    1.42
     ibiza
    1.42
     secon
    1.40
     Minang
    1.40
     unden
    1.40
    Activations Density 0.296%

    No Known Activations