© 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. 14381
    Prev
    Next
    INDEX
    Explanations

    formatting and structural elements within documents

    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
    419
    +0.19
    1.1%
    181
    +0.17
    1.0%
    263
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.19
    0.13
    433
    +0.17
    0.06
    419
    +0.15
    0.08
    Negative Logits
    Ļª
    -2.51
    ¿½
    -2.21
    Ļ
    -2.18
    £
    -2.11
    ĭ
    -2.04
    ģ
    -2.01
    Ī
    -2.00
    ľĵ
    -2.00
    º
    -1.99
    ¿
    -1.97
    POSITIVE LOGITS
    1371
    1.55
     ">
    1.39
     Fig
    1.38
    uild
    1.33
     Instruments
    1.31
    elen
    1.28
    clair
    1.27
     WARRANTY
    1.26
    illo
    1.25
    ardo
    1.24
    Activations Density 3.940%

    No Known Activations