© 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. 2-RES-SM
    11. 32534
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases emphasizing excess or extremity

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    335
    +0.12
    0.6%
    14
    +0.11
    0.6%
    5
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.12
    0.04
    301
    +0.11
    0.03
    5
    +0.10
    0.03
    Negative Logits
    ¿
    -2.39
    Ĵ
    -2.17
    £
    -2.15
    ĸ
    -2.13
    °
    -2.09
    ¨
    -2.05
    ļ
    -2.03
    ©
    -2.03
    ²
    -2.02
    IJ
    -2.00
    POSITIVE LOGITS
     hurry
    1.66
     expensive
    1.50
    renew
    1.50
     frank
    1.45
     priced
    1.41
    gni
    1.40
     coward
    1.40
     inexpensive
    1.35
    expensive
    1.35
     moderate
    1.34
    Activations Density 0.155%

    No Known Activations