© 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. 2-RES-SM
    11. 10233
    Prev
    Next
    INDEX
    Explanations

    terms related to rheumatoid arthritis and its symptoms

    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
    321
    +0.15
    0.8%
    156
    +0.13
    0.7%
    147
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.15
    0.02
    19
    +0.13
    0.02
    271
    +0.12
    -0.00
    Negative Logits
    mates
    -1.72
     mates
    -1.70
     vez
    -1.63
     complimentary
    -1.62
    aware
    -1.59
     lucky
    -1.48
     polite
    -1.47
    boards
    -1.45
     undercover
    -1.44
     temps
    -1.44
    POSITIVE LOGITS
     arthritis
    1.86
    arth
    1.73
    »¿
    1.65
    iously
    1.65
     disease
    1.54
    InstanceState
    1.51
     inflammation
    1.50
    izumab
    1.49
    ³
    1.45
    THER
    1.45
    Activations Density 0.114%

    No Known Activations