© 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. 10475
    Prev
    Next
    INDEX
    Explanations

    terms related to fetal and neonatal health

    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
    156
    +0.16
    0.9%
    124
    +0.12
    0.7%
    411
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.16
    0.02
    362
    +0.12
    0.02
    124
    +0.12
    0.02
    Negative Logits
    heet
    -1.69
    paces
    -1.66
    patcher
    -1.57
    ftware
    -1.51
    heets
    -1.51
     cref
    -1.47
    amp
    -1.42
    >&
    -1.39
    herent
    -1.38
     VPN
    -1.38
    POSITIVE LOGITS
    ĻĤ
    2.94
    ľĵ
    2.57
    ĸ´
    2.38
     mortality
    2.32
    º
    2.31
    »¿
    2.29
     deaths
    2.23
    ´
    2.20
    ļ
    2.15
    ħ
    2.13
    Activations Density 0.117%

    No Known Activations