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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 37
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions related to financial sectors, sovereign power, bailout packages, and fiscal stimulus

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1637
    +0.08
    0.2%
    478
    +0.08
    0.2%
    1376
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.08
    0.02
    1094
    +0.08
    0.02
    1910
    +0.08
    0.02
    Negative Logits
    Personendaten
    -0.63
     camp
    -0.59
    camp
    -0.54
    理工
    -0.53
     Camp
    -0.53
    cart
    -0.53
    HMIS
    -0.52
    ieteur
    -0.52
     Cart
    -0.51
    uyasha
    -0.50
    POSITIVE LOGITS
     sovereign
    2.77
     Sovereign
    2.28
    vereign
    2.06
     sovereignty
    1.97
     sovereigns
    1.80
    vereignty
    1.66
     souverain
    1.40
     sovere
    1.29
     sover
    1.28
     toledo
    1.26
    Activations Density 0.258%

    No Known Activations