© 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. 28625
    Prev
    Next
    INDEX
    Explanations

    biochemical components and structural features of proteins, particularly focusing on amino acids and their arrangements

    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
    275
    +0.13
    0.7%
    466
    +0.12
    0.7%
    33
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.13
    0.01
    26
    +0.12
    0.01
    385
    +0.11
    0.01
    Negative Logits
    aid
    -1.81
    oard
    -1.69
    ')->
    -1.67
    ı
    -1.62
     sudden
    -1.59
    ½
    -1.58
    ){
    -1.52
    icable
    -1.50
    ediatric
    -1.47
    )){
    -1.46
    POSITIVE LOGITS
     residues
    2.45
     residue
    2.08
    erved
    1.93
     epitopes
    1.88
     amino
    1.84
     peptides
    1.71
     Glu
    1.71
    tagged
    1.68
     Cys
    1.67
     conserved
    1.64
    Activations Density 0.191%

    No Known Activations