© 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. 2-RES-SM
    11. 31666
    Prev
    Next
    INDEX
    Explanations

    phrases indicating capability or potential

    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
    186
    +0.18
    1.0%
    69
    +0.16
    0.9%
    150
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.18
    0.10
    406
    +0.16
    0.08
    411
    +0.12
    0.06
    Negative Logits
     parallels
    -1.69
     implications
    -1.58
    clud
    -1.50
     aside
    -1.47
    etus
    -1.45
    erna
    -1.44
    avia
    -1.42
    ĸ
    -1.41
    wich
    -1.41
    ¡
    -1.39
    POSITIVE LOGITS
     reproduce
    2.08
     disclose
    1.86
     engage
    1.81
     communicate
    1.75
     earn
    1.74
     adequately
    1.73
     efficiently
    1.73
     indefinitely
    1.72
     capture
    1.70
     receive
    1.70
    Activations Density 0.542%

    No Known Activations