© 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. 4-RES-SM
    11. 12517
    Prev
    Next
    INDEX
    Explanations

    expressions of nostalgia or emotional reminiscence

    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
    +0.19
    1.1%
    350
    +0.14
    0.8%
    313
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.19
    0.05
    340
    +0.14
    0.03
    326
    +0.12
    0.04
    Negative Logits
     ratios
    -1.69
     computed
    -1.64
     presence
    -1.64
    č↵č↵č
    -1.60
     ratio
    -1.59
    ieurs
    -1.52
     Figures
    -1.48
     figure
    -1.46
    č↵č
    -1.44
     Section
    -1.44
    POSITIVE LOGITS
    Ļª
    4.91
    ¼
    4.89
    ½
    4.88
    Ģ
    4.43
    ħ
    4.40
    ®
    4.40
    ¿
    4.35
    »
    4.30
    ´
    4.29
    Į
    4.23
    Activations Density 0.222%

    No Known Activations