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. 15778
    Prev
    Next
    INDEX
    Explanations

    phrases related to work and organizational roles, particularly in the context of a company or institution

    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
    227
    +0.17
    0.5%
    1870
    +0.17
    0.5%
    1241
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.05
    356
    +0.17
    0.02
    1870
    +0.09
    0.02
    Negative Logits
     friable
    -0.67
     blackish
    -0.62
     mutagen
    -0.60
     loamy
    -0.58
     inext
    -0.58
     grayish
    -0.55
     Thine
    -0.54
     discolor
    -0.53
     greyish
    -0.53
     blest
    -0.52
    POSITIVE LOGITS
     monaster
    0.88
     teras
    0.78
     Mémoires
    0.75
     Personne
    0.75
     Autó
    0.74
     pixabay
    0.73
     españa
    0.72
     republi
    0.71
    তথ্যসূত্র
    0.70
     makro
    0.69
    Activations Density 0.148%

    No Known Activations