© 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. 4-RES-SM
    11. 13406
    Prev
    Next
    INDEX
    Explanations

    occurrences of oxidative compounds and related terminology

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.12
    0.7%
    315
    +0.12
    0.7%
    27
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.12
    0.02
    61
    +0.12
    0.01
    98
    +0.11
    0.01
    Negative Logits
     quarters
    -1.65
    iginally
    -1.50
    rent
    -1.49
     opinions
    -1.48
    ware
    -1.44
     string
    -1.43
     OPINION
    -1.42
     decisions
    -1.38
     supre
    -1.38
     ordinary
    -1.37
    POSITIVE LOGITS
    idation
    2.80
    ĥ
    2.55
    etine
    2.42
    º
    2.34
    idase
    2.27
    ¼
    2.25
    Ģ
    2.23
    ·¸
    2.20
    Ł
    2.12
    ²
    2.10
    Activations Density 0.043%

    No Known Activations