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. 10065
    Prev
    Next
    INDEX
    Explanations

    words related to being cautious, deliberate, and discerning in decision-making and actions

    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
    1013
    +0.12
    0.3%
    605
    +0.10
    0.3%
    420
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.12
    0.05
    284
    +0.10
    0.05
    2044
    +0.10
    0.06
    Negative Logits
     effe
    -1.34
     fte
    -1.34
     pessi
    -1.31
     seiz
    -1.30
     fta
    -1.30
     emphat
    -1.29
     perciò
    -1.28
     poichè
    -1.27
     noel
    -1.27
     fup
    -1.27
    POSITIVE LOGITS
     about
    0.87
     towards
    0.78
     regarding
    0.76
     toward
    0.75
     against
    0.71
    about
    0.70
     with
    0.69
     in
    0.66
     throughout
    0.66
     during
    0.66
    Activations Density 0.302%

    No Known Activations