© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11644
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to mental health issues, specifically depression and its associated symptoms and impacts

    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
    186
    +0.16
    0.9%
    21
    +0.14
    0.8%
    348
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.16
    0.05
    92
    +0.14
    0.01
    407
    +0.13
    0.01
    Negative Logits
     hereto
    -1.68
    ionale
    -1.59
    uese
    -1.58
    illery
    -1.55
    ERN
    -1.55
    ément
    -1.53
     Marine
    -1.50
     donate
    -1.42
    hers
    -1.41
     flown
    -1.40
    POSITIVE LOGITS
     symptoms
    2.91
     disorder
    2.90
     disorders
    2.83
     Disorder
    2.61
     syndrome
    2.48
     mood
    2.47
     syndromes
    2.45
     psychosis
    2.24
     sympt
    2.19
     Disorders
    2.19
    Activations Density 0.317%

    No Known Activations