© 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. 14174
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to biology and anthropology, including publications and research references

    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
    107
    +0.15
    0.9%
    255
    +0.14
    0.8%
    315
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.15
    0.04
    248
    +0.14
    0.03
    425
    +0.13
    0.04
    Negative Logits
    ¢
    -1.70
     eternity
    -1.69
     waiting
    -1.63
    acha
    -1.60
    hell
    -1.57
    placeholder
    -1.56
    itel
    -1.50
    Ļª
    -1.50
    antically
    -1.49
    iplex
    -1.49
    POSITIVE LOGITS
     Journal
    2.36
     Proceedings
    2.34
     Appl
    2.28
     Handbook
    2.25
    Verlag
    2.22
     eds
    2.19
     Essays
    2.17
     Publication
    2.17
     Papers
    2.16
     DOI
    2.16
    Activations Density 0.356%

    No Known Activations