© 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. 25892
    Prev
    Next
    INDEX
    Explanations

    articles and expressions relating to quantity or designation

    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
    505
    +0.12
    0.7%
    450
    +0.12
    0.7%
    72
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.12
    0.07
    319
    +0.12
    0.05
    72
    +0.12
    0.05
    Negative Logits
    ĻĤ
    -2.21
    Ķ
    -2.20
    ı
    -2.05
    ¢
    -1.98
    ”)
    -1.90
    £
    -1.90
    ŀ
    -1.87
    ķ
    -1.85
    ĺ
    -1.84
    Į
    -1.80
    POSITIVE LOGITS
    vez
    1.50
     Honor
    1.46
     someday
    1.45
    UG
    1.41
     bets
    1.38
     Android
    1.37
    laid
    1.37
     ^[@
    1.34
    zier
    1.33
     Ãħ
    1.29
    Activations Density 0.784%

    No Known Activations