© 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. 13560
    Prev
    Next
    INDEX
    Explanations

    references to studies or findings regarding mental health and its impact on creativity

    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
    307
    +0.27
    1.5%
    498
    +0.13
    0.8%
    134
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.27
    0.05
    307
    +0.13
    0.10
    306
    +0.13
    0.04
    Negative Logits
    µ
    -2.72
    ī
    -2.66
    Ŀ
    -2.47
    ŀ
    -2.47
    ª
    -2.39
    ¨
    -2.37
    §
    -2.37
    ·
    -2.36
    Ĺ
    -2.35
    ¶
    -2.32
    POSITIVE LOGITS
     surveys
    3.03
     study
    2.94
     studies
    2.84
     Study
    2.80
     analyses
    2.77
     survey
    2.66
     Findings
    2.64
    Study
    2.63
     questionnaires
    2.59
    study
    2.57
    Activations Density 1.471%

    No Known Activations