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. 2952
    Prev
    Next
    INDEX
    Explanations

    references to teamwork and collaboration

    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
    1533
    +0.10
    0.3%
    1252
    +0.08
    0.2%
    658
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1533
    +0.10
    0.02
    658
    +0.08
    0.06
    1786
    +0.07
    0.01
    Negative Logits
     Kela
    -0.48
     dises
    -0.47
     Abp
    -0.46
    {*}
    -0.45
     anhyd
    -0.44
    *</
    -0.44
    uklu
    -0.43
    Tembelea
    -0.42
     disambiguazione
    -0.42
     abbin
    -0.42
    POSITIVE LOGITS
     collectively
    0.97
     shared
    0.86
     together
    0.84
     sharing
    0.81
     collective
    0.81
     camaraderie
    0.78
     unison
    0.77
     collaboratively
    0.77
     TOGETHER
    0.76
     mutually
    0.76
    Activations Density 0.811%

    No Known Activations