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. 13230
    Prev
    Next
    INDEX
    Explanations

    praise or criticism towards individuals or organizations

    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
    478
    +0.11
    0.3%
    1823
    +0.08
    0.2%
    872
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.11
    0.05
    1823
    +0.08
    0.04
    756
    +0.07
    0.05
    Negative Logits
     encomp
    -1.69
     Juf
    -1.67
     squa
    -1.64
     depic
    -1.62
     reluct
    -1.61
     increa
    -1.59
     secon
    -1.57
     shenan
    -1.56
     disagre
    -1.54
     fortn
    -1.52
    POSITIVE LOGITS
     genuinely
    0.74
     correctly
    0.71
     wisely
    0.69
    /*---
    0.66
     courage
    0.65
     thoughtful
    0.65
     truly
    0.65
     sensib
    0.64
     compassion
    0.64
     consistently
    0.63
    Activations Density 0.522%

    No Known Activations