© 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. 23937
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and configurations

    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
    156
    +0.41
    2.5%
    17
    +0.19
    1.1%
    136
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.41
    0.06
    156
    +0.19
    0.09
    90
    +0.11
    0.09
    Negative Logits
     sorry
    -1.63
    TRODUCTION
    -1.60
    awk
    -1.44
    ]{}]{}
    -1.43
     ERROR
    -1.27
    dden
    -1.26
     thank
    -1.26
    ↵
    -1.25
     hepat
    -1.25
     Cong
    -1.25
    POSITIVE LOGITS
    ®
    2.52
    ¾
    2.37
    Ļ
    2.29
    Ħ
    2.21
    ³
    2.19
    Ĥ
    2.19
    §
    2.18
    ¯
    1.96
    ĥ
    1.95
    ¿
    1.94
    Activations Density 0.773%

    No Known Activations