Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 744
    Prev
    Next
    INDEX
    Explanations

    phrases related to company growth and team composition

    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
    +0.37
    1.4%
    1013
    +0.12
    0.5%
    227
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1403
    +0.37
    0.00
    227
    +0.12
    0.07
    288
    +0.12
    0.05
    Negative Logits
    <bos>
    -1.93
    getMinutes
    -0.70
    }{||
    -0.69
    ///
    -0.61
    ModelAttribute
    -0.61
    override
    -0.60
    remove
    -0.60
    else
    -0.60
    AddWithValue
    -0.60
    addComponent
    -0.59
    POSITIVE LOGITS
     accla
    1.96
     maneu
    1.93
     increa
    1.86
     impra
    1.83
     hairc
    1.82
     affor
    1.80
     inev
    1.74
     reluct
    1.73
     swarovski
    1.73
     jurassic
    1.72
    Activations Density 1.348%

    No Known Activations