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. 8449
    Prev
    Next
    INDEX
    Explanations

    information related to archaeological discoveries and research projects

    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
    939
    +0.13
    0.4%
    906
    +0.12
    0.4%
    1013
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.13
    0.06
    548
    +0.12
    0.06
    194
    +0.12
    0.02
    Negative Logits
     utop
    -0.91
     plak
    -0.88
     elek
    -0.87
     lapto
    -0.85
     kask
    -0.84
     karton
    -0.83
     kade
    -0.82
     hek
    -0.82
     boks
    -0.81
     moza
    -0.81
    POSITIVE LOGITS
     archaeologists
    0.71
     excavations
    0.68
     archaeological
    0.66
     excavated
    0.65
     liberality
    0.64
     Archaeological
    0.63
     excavation
    0.63
     archaeology
    0.61
     discoveries
    0.61
     qp
    0.60
    Activations Density 0.622%

    No Known Activations