© 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. 30090
    Prev
    Next
    INDEX
    Explanations

    references to roads and related infrastructure

    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
    184
    +0.13
    0.8%
    466
    +0.13
    0.7%
    115
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.13
    0.03
    96
    +0.13
    0.03
    114
    +0.11
    0.03
    Negative Logits
     sexes
    -1.66
    ureus
    -1.63
     paternal
    -1.61
     dignity
    -1.59
    TRODUCTION
    -1.53
     pituitary
    -1.53
     primordial
    -1.51
     gonad
    -1.51
     breasts
    -1.50
     malignant
    -1.50
    POSITIVE LOGITS
    blocks
    2.06
    block
    1.89
    ways
    1.86
    abouts
    1.86
    gap
    1.74
    yard
    1.64
    roads
    1.63
    casts
    1.60
    ios
    1.59
     Tours
    1.57
    Activations Density 0.119%

    No Known Activations