© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14262
    Prev
    Next
    INDEX
    Explanations

    mentions of the act of inventing or inventions

    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
    1068
    +0.14
    0.6%
    1406
    +0.14
    0.5%
    1515
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.14
    0.02
    1406
    +0.14
    0.02
    1068
    +0.13
    0.02
    Negative Logits
     juf
    -0.53
     meis
    -0.49
     Slu
    -0.49
     haer
    -0.48
     Boek
    -0.47
     minimale
    -0.47
    Wies
    -0.47
     Heere
    -0.47
     purcha
    -0.47
     coö
    -0.46
    POSITIVE LOGITS
     invent
    1.01
    invent
    1.01
     invention
    0.98
     invented
    0.97
     inventor
    0.96
     inventions
    0.94
     Invent
    0.94
     inventing
    0.94
    Invent
    0.94
    invention
    0.93
    Activations Density 0.074%

    No Known Activations