© 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 EvalsExportsinterp-engineNEWAPI 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. 14607
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular binding and interactions

    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
    348
    +0.15
    0.9%
    426
    +0.12
    0.7%
    496
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.15
    0.01
    47
    +0.12
    0.02
    426
    +0.12
    0.02
    Negative Logits
    say
    -1.78
    érie
    -1.67
     retire
    -1.63
     educated
    -1.59
    ediatric
    -1.57
    school
    -1.50
    education
    -1.45
    uvre
    -1.45
    lege
    -1.44
    ÄŁ
    -1.43
    POSITIVE LOGITS
     affinity
    2.22
     proteins
    2.17
     sites
    2.15
     ligands
    2.08
     capacity
    2.06
     protein
    1.98
     constants
    1.93
     ligand
    1.93
     Sites
    1.88
    ANCE
    1.86
    Activations Density 0.124%

    No Known Activations