© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 10842
    Prev
    Next
    INDEX
    Explanations

    information related to corporate financial transactions and acquisitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    203
    +0.15
    0.8%
    79
    +0.14
    0.8%
    320
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    79
    +0.15
    0.18
    320
    +0.14
    0.17
    111
    +0.11
    0.13
    Negative Logits
    ĻĤ
    -2.63
    »
    -2.15
    Ĺ
    -2.14
    ĨĴ
    -2.13
    Ľ
    -1.96
    Ļª
    -1.95
    ij
    -1.90
    Īĺ
    -1.89
    £
    -1.85
    Ģ
    -1.84
    POSITIVE LOGITS
     shareholders
    3.58
     shareholder
    3.45
     investors
    3.38
     companies
    3.27
     investor
    3.14
     firms
    3.09
     business
    3.09
     executives
    2.98
     corporation
    2.98
     company
    2.97
    Activations Density 3.327%

    No Known Activations