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. 1610
    Prev
    Next
    INDEX
    Explanations

    information related to teamwork and collaboration in a professional setting

    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
    478
    +0.14
    0.4%
    658
    +0.13
    0.4%
    906
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.14
    0.11
    862
    +0.13
    0.06
    47
    +0.10
    0.06
    Negative Logits
     milf
    -1.05
     increa
    -1.04
     bandung
    -1.03
     maneu
    -1.00
     véhic
    -0.99
     carrefour
    -0.97
     hairc
    -0.96
     strick
    -0.95
     obé
    -0.94
     hentai
    -0.94
    POSITIVE LOGITS
     asleep
    0.75
     engaged
    0.73
     wearing
    0.72
     alive
    0.70
     ready
    0.70
     preparing
    0.69
    Estou
    0.69
     enjoying
    0.69
     able
    0.69
     playing
    0.68
    Activations Density 0.516%

    No Known Activations