© 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. 8795
    Prev
    Next
    INDEX
    Explanations

    references to specific historical periods and their characteristics

    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
    422
    +0.13
    0.7%
    427
    +0.11
    0.6%
    374
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    427
    +0.13
    0.07
    145
    +0.11
    0.06
    460
    +0.11
    0.04
    Negative Logits
    ³
    -2.13
    ľĵ
    -2.00
    Ļª
    -1.92
    ĻĤ
    -1.90
    ¹
    -1.86
    Ļ
    -1.86
    Į
    -1.86
    ½
    -1.80
    ·¸
    -1.76
    ®
    -1.74
    POSITIVE LOGITS
     century
    3.51
    century
    2.85
     millennium
    2.76
     centuries
    2.69
     1980
    2.60
     decade
    2.58
     era
    2.57
     1960
    2.51
     1940
    2.51
     1990
    2.51
    Activations Density 0.548%

    No Known Activations