© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23784
    Prev
    Next
    INDEX
    Explanations

    The effects of financial downturns and challenges in various sectors

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    17
    +0.21
    1.2%
    337
    +0.13
    0.7%
    248
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.21
    0.10
    226
    +0.13
    0.04
    8
    +0.13
    0.03
    Negative Logits
     promise
    -1.52
     Himself
    -1.47
     nature
    -1.44
     caution
    -1.42
     editors
    -1.37
     dressed
    -1.37
     promises
    -1.36
     them
    -1.35
     trusted
    -1.35
    hurst
    -1.34
    POSITIVE LOGITS
    ICT
    1.73
    uar
    1.46
    rá
    1.45
    .","
    1.42
    acts
    1.40
    uesta
    1.40
     adversely
    1.35
    iff
    1.34
    amble
    1.32
    occup
    1.32
    Activations Density 2.910%

    No Known Activations