© 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. 1-RES-SM
    11. 26370
    Prev
    Next
    INDEX
    Explanations

    the word 'or' in various contexts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    478
    +0.21
    1.2%
    191
    +0.12
    0.7%
    95
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.21
    0.03
    494
    +0.12
    0.02
    288
    +0.12
    0.03
    Negative Logits
    heads
    -1.92
    ľĵ
    -1.72
    []{
    -1.64
    àµį
    -1.53
    age
    -1.51
    ¢
    -1.50
    head
    -1.48
    stown
    -1.47
    §
    -1.45
    worth
    -1.45
    POSITIVE LOGITS
    amycin
    1.66
     anything
    1.65
     any
    1.55
    icense
    1.52
    idem
    1.52
     punish
    1.50
    cgi
    1.43
     GPL
    1.42
     cert
    1.42
     pronounce
    1.42
    Activations Density 0.132%

    No Known Activations