© 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 EvalsExportsAPI 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. 25763
    Prev
    Next
    INDEX
    Explanations

    terms related to regulations and conditions affecting populations, particularly in a health or administrative context

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.18
    1.0%
    111
    +0.15
    0.8%
    413
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.04
    271
    +0.15
    0.01
    311
    +0.13
    0.03
    Negative Logits
    rish
    -1.46
     maternal
    -1.40
     synd
    -1.38
     realized
    -1.36
     introduced
    -1.36
    ophen
    -1.35
     aging
    -1.35
     coined
    -1.34
     realised
    -1.33
     described
    -1.33
    POSITIVE LOGITS
    ubicin
    1.78
    "}](#
    1.63
    URAL
    1.47
    plain
    1.46
    ίαÏĤ
    1.42
    oqu
    1.40
    imum
    1.33
    éĩĮ
    1.33
    ем
    1.31
    idable
    1.30
    Activations Density 0.196%

    No Known Activations