© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 13340
    Prev
    Next
    INDEX
    Explanations

    data related to significant economic losses and stock performance

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    262
    +0.14
    0.8%
    314
    +0.13
    0.7%
    320
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.14
    0.06
    262
    +0.13
    0.05
    314
    +0.11
    0.10
    Negative Logits
    ĻĤ
    -2.87
    º
    -2.71
    ³
    -2.67
    ĸ´
    -2.53
    ·¸
    -2.52
    ´
    -2.43
    ±
    -2.34
    ij
    -2.30
    ¼
    -2.29
    ĭ
    -2.28
    POSITIVE LOGITS
     investors
    2.68
     volatility
    2.34
     fiscal
    2.28
     recession
    2.21
     investor
    2.20
     GDP
    2.18
     tariffs
    2.17
     trading
    2.17
     economists
    2.12
     revenue
    2.11
    Activations Density 4.235%

    No Known Activations