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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15910
    Prev
    Next
    INDEX
    Explanations

    information about retail industry trends, such as wage increases, business decisions, and impact on employees

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1403
    +0.12
    0.4%
    1385
    +0.10
    0.3%
    1526
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1347
    +0.12
    0.05
    235
    +0.10
    0.04
    274
    +0.09
    0.03
    Negative Logits
     disagre
    -1.66
     intersper
    -1.61
     emphat
    -1.57
     depic
    -1.55
     apprehen
    -1.54
     indestru
    -1.53
     increa
    -1.53
     affor
    -1.53
     shenan
    -1.52
     hentai
    -1.52
    POSITIVE LOGITS
     shopping
    1.01
     retail
    0.94
     retailer
    0.92
     stores
    0.92
     store
    0.92
     retailers
    0.92
     shoppers
    0.91
     Shopping
    0.84
     shop
    0.83
     shops
    0.81
    Activations Density 0.714%

    No Known Activations