Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8137
    Prev
    Next
    INDEX
    Explanations

    phrases related to power, influence, and authority

    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
    130
    +0.14
    0.5%
    410
    +0.14
    0.5%
    1616
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.14
    0.03
    1616
    +0.14
    0.03
    410
    +0.13
    0.03
    Negative Logits
    Chham
    -0.57
    Litteratur
    -0.53
     patrio
    -0.52
    Lá
    -0.50
    marzo
    -0.48
    Kilder
    -0.47
    Tē
    -0.46
    ›
    -0.46
    Viernes
    -0.46
    Saat
    -0.45
    POSITIVE LOGITS
     influence
    1.20
     Influence
    1.18
     influences
    1.17
     Influences
    1.16
    influence
    1.09
    Influence
    1.06
     influencing
    1.05
     INFLUENCE
    1.03
     Influ
    1.02
     influenced
    0.99
    Activations Density 0.082%

    No Known Activations