© 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. 1-RES-SM
    11. 24361
    Prev
    Next
    INDEX
    Explanations

    terms related to financial investments

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    406
    +0.14
    0.8%
    156
    +0.13
    0.8%
    29
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.14
    0.03
    85
    +0.13
    0.03
    187
    +0.11
    0.03
    Negative Logits
    ĨĴ
    -3.76
    ¿
    -3.59
    ²
    -3.52
    Ĥ¬
    -3.51
    ©
    -3.41
    Ļª
    -3.40
    ´
    -3.39
    »
    -3.34
    ½
    -3.30
    º
    -3.29
    POSITIVE LOGITS
     banker
    1.85
     bankers
    1.79
    iem
    1.73
     banks
    1.73
     resistor
    1.66
    econom
    1.61
     bank
    1.54
     deposits
    1.54
     trusts
    1.48
     cubes
    1.48
    Activations Density 0.144%

    No Known Activations