© 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. 1-RES-SM
    11. 29290
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss concepts of restoration or recovery from physical or emotional states

    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
    +0.13
    0.7%
    249
    +0.12
    0.7%
    385
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.13
    0.04
    98
    +0.12
    -0.02
    315
    +0.12
    0.06
    Negative Logits
    Ļ
    -1.61
    Ĵ
    -1.61
    ĨĴ
    -1.61
    į
    -1.55
    ¾
    -1.50
    :"){
    -1.49
    Ĩ
    -1.48
    «
    -1.43
    ±
    -1.42
    Ī
    -1.42
    POSITIVE LOGITS
     Clause
    1.59
    velt
    1.56
     alike
    1.55
    walls
    1.49
    jan
    1.48
    hers
    1.41
     symmetries
    1.39
    achel
    1.35
    isans
    1.34
    vers
    1.33
    Activations Density 1.243%

    No Known Activations