© 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. 4-RES-SM
    11. 15384
    Prev
    Next
    INDEX
    Explanations

    references to prices and product reviews

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    64
    +0.14
    0.7%
    11
    +0.12
    0.6%
    183
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.14
    0.08
    106
    +0.12
    0.03
    29
    +0.11
    0.00
    Negative Logits
     Tex
    -1.86
     Keller
    -1.74
     Lub
    -1.73
     Pitts
    -1.69
     Worcester
    -1.65
    č↵
    -1.52
     Hew
    -1.51
     Bos
    -1.47
     CDs
    -1.46
    immun
    -1.44
    POSITIVE LOGITS
     2019
    3.63
     2018
    3.61
     2017
    3.42
     2020
    3.42
     Trump
    3.13
    2018
    3.08
    2019
    3.01
     2016
    2.98
    2017
    2.86
     2021
    2.71
    Activations Density 1.802%

    No Known Activations