© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27237
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe odd or abnormal situations

    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
    156
    +0.23
    1.3%
    466
    +0.13
    0.7%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.23
    0.03
    466
    +0.13
    0.02
    359
    +0.12
    0.02
    Negative Logits
    ëĭĪëĭ¤
    -1.63
    +.
    -1.55
    antage
    -1.48
    apon
    -1.42
    md
    -1.40
    xiv
    -1.39
     âī¥
    -1.38
     superior
    -1.38
    ursuant
    -1.38
     viability
    -1.37
    POSITIVE LOGITS
    ¿½
    2.36
    ¨
    2.15
    ĩ
    2.07
    Ł
    2.06
     ones
    2.00
    ®
    1.95
    ±
    1.93
    °
    1.90
     things
    1.89
    ĻĤ
    1.84
    Activations Density 0.154%

    No Known Activations