© 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. 13844
    Prev
    Next
    INDEX
    Explanations

    references to market dynamics and conditions

    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
    156
    +0.15
    0.9%
    173
    +0.12
    0.7%
    34
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.15
    0.03
    34
    +0.12
    0.03
    64
    +0.11
    0.02
    Negative Logits
    ³
    -1.95
    ndef
    -1.94
    IJ
    -1.83
    unnumbered
    -1.78
    ´
    -1.75
    SEQUENTIAL
    -1.67
     peritoneal
    -1.65
    º
    -1.61
    öm
    -1.56
     subd
    -1.54
    POSITIVE LOGITS
    places
    2.58
    bank
    1.81
    eer
    1.81
     price
    1.74
    maker
    1.69
    place
    1.68
     stall
    1.64
     prices
    1.64
    vation
    1.64
     situation
    1.62
    Activations Density 0.129%

    No Known Activations