© 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. 9880
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatments and their efficacy

    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
    156
    +0.13
    0.7%
    356
    +0.11
    0.6%
    184
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    361
    +0.13
    0.02
    418
    +0.11
    0.00
    356
    +0.11
    0.02
    Negative Logits
    ŀ
    -2.65
    ķ
    -2.54
    ĥ½
    -2.37
    ®
    -2.32
    ¿
    -2.21
    ¾
    -2.18
    µ
    -2.16
    Ŀ
    -2.13
    GREEK
    -2.11
    Ĵ
    -2.11
    POSITIVE LOGITS
     outcome
    1.86
     options
    1.84
     regimens
    1.68
     favour
    1.68
     schedule
    1.65
     efficacy
    1.62
     regimen
    1.60
     modalities
    1.56
     delay
    1.53
     schedules
    1.53
    Activations Density 0.044%

    No Known Activations