© 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. 13117
    Prev
    Next
    INDEX
    Explanations

    references to mental health issues and conditions

    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
    492
    +0.14
    0.8%
    331
    +0.14
    0.8%
    2
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.14
    0.02
    492
    +0.14
    0.02
    331
    +0.11
    0.02
    Negative Logits
    Ķ
    -1.86
    matically
    -1.77
    ments
    -1.65
    rium
    -1.57
     moi
    -1.57
    ĭ
    -1.56
    antly
    -1.53
    ^*\
    -1.46
    Ģ
    -1.44
    imab
    -1.43
    POSITIVE LOGITS
     health
    2.20
     retardation
    2.15
     disorders
    2.12
     anguish
    2.07
    health
    2.00
     illness
    1.96
     disabilities
    1.90
     illnesses
    1.86
    ty
    1.76
     Disorders
    1.74
    Activations Density 0.079%

    No Known Activations