© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 14095
    Prev
    Next
    INDEX
    Explanations

    concepts related to mental health, stigma, and their impact on life quality

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    312
    +0.15
    0.9%
    436
    +0.13
    0.7%
    157
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.15
    -0.01
    312
    +0.13
    0.05
    335
    +0.12
    0.05
    Negative Logits
     prosecute
    -1.61
     secrets
    -1.55
     oceans
    -1.52
     rogue
    -1.48
     desert
    -1.48
     beaches
    -1.47
    engeance
    -1.47
     enemies
    -1.47
     wrong
    -1.45
     bad
    -1.45
    POSITIVE LOGITS
     questionnaire
    2.55
    Participants
    2.16
     Participants
    2.15
     questionnaires
    2.15
     consisted
    2.15
     participant
    2.06
     SPSS
    2.04
     participants
    1.99
     Questionnaire
    1.91
    icipants
    1.84
    Activations Density 1.036%

    No Known Activations