© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11401
    Prev
    Next
    INDEX
    Explanations

    medical and diagnostic terms relating to conditions and examinations

    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
    7
    +0.12
    0.7%
    12
    +0.12
    0.7%
    153
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.12
    0.00
    153
    +0.12
    0.03
    413
    +0.12
    0.01
    Negative Logits
     proposition
    -1.87
     premium
    -1.82
     fare
    -1.72
     policy
    -1.67
     priority
    -1.66
     price
    -1.66
     finance
    -1.61
     investor
    -1.54
     asset
    -1.52
     expires
    -1.52
    POSITIVE LOGITS
     staining
    2.66
     stained
    2.55
     stains
    2.37
     stain
    2.16
     lesions
    2.04
     morphology
    1.98
     specimens
    1.97
     lining
    1.96
     visualized
    1.93
     pores
    1.93
    Activations Density 0.779%

    No Known Activations