© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13992
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and opinions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    21
    +0.20
    1.2%
    148
    +0.10
    0.6%
    410
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.20
    0.01
    148
    +0.10
    0.02
    65
    +0.10
    0.04
    Negative Logits
     itself
    -1.51
    ises
    -1.42
    ester
    -1.42
     IE
    -1.37
    las
    -1.35
     Press
    -1.34
    aret
    -1.34
     wells
    -1.28
    aler
    -1.28
    itian
    -1.25
    POSITIVE LOGITS
    ĵ
    3.90
    §
    3.73
    º
    3.65
    Ī
    3.63
    ®
    3.62
    Ĵ
    3.61
    ¿
    3.59
    ĨĴ
    3.54
    ª
    3.53
    ¸
    3.53
    Activations Density 0.158%

    No Known Activations