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. 216
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to energy sources and strategies

    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
    1222
    +0.17
    0.7%
    1233
    +0.17
    0.7%
    1937
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.17
    0.05
    1222
    +0.17
    0.04
    1806
    +0.15
    0.04
    Negative Logits
     unspeak
    -0.67
     intrigu
    -0.63
     glimp
    -0.63
     encomp
    -0.62
     indescri
    -0.61
     cristina
    -0.59
     exult
    -0.59
     implacable
    -0.59
     intersper
    -0.58
     philanth
    -0.58
    POSITIVE LOGITS
     energy
    1.39
    energy
    1.32
     ENERGY
    1.31
     Energy
    1.30
    Energy
    1.29
    ENERGY
    1.20
     energies
    1.11
    energies
    0.94
     Energie
    0.88
     energía
    0.88
    Activations Density 0.073%

    No Known Activations