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. 6-RES-JB
    6. 14601
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial portfolios

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.14
    0.8%
    1562
    +0.14
    0.7%
    50
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.14
    0.03
    1052
    +0.14
    0.02
    990
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.64
     intersper
    -1.31
     shenan
    -1.00
     apprehen
    -0.99
     encomp
    -0.98
     shuddered
    -0.97
     trod
    -0.95
    /***
    
    -0.94
    /**
    -0.93
    ⓧ
    -0.93
    POSITIVE LOGITS
     portfolio
    1.51
    Portfolio
    1.39
     Portfolio
    1.37
    portfolio
    1.31
     portfolios
    1.22
    FOLIO
    1.01
    folios
    0.94
     cartera
    0.76
    folio
    0.70
     galeria
    0.69
    Activations Density 0.206%

    No Known Activations