© 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. 13235
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to medical imaging and therapeutics

    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
    248
    +0.11
    0.6%
    383
    +0.10
    0.5%
    183
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.11
    0.01
    248
    +0.10
    0.02
    47
    +0.10
    0.02
    Negative Logits
     debts
    -2.03
     pest
    -2.00
     plantation
    -1.95
     homestead
    -1.94
     creditors
    -1.91
     germination
    -1.91
     weeds
    -1.90
     foreclosure
    -1.90
     boil
    -1.89
     Loan
    -1.88
    POSITIVE LOGITS
     imaging
    3.71
     MRI
    3.55
     scans
    3.37
    MRI
    3.32
     Imaging
    3.29
    imaging
    3.19
     imaged
    2.85
     voxel
    2.84
     scan
    2.82
     scanner
    2.79
    Activations Density 0.247%

    No Known Activations