© 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. 2-RES-SM
    11. 30320
    Prev
    Next
    INDEX
    Explanations

    references to sports events and awards

    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
    96
    +0.13
    0.7%
    212
    +0.13
    0.7%
    442
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.13
    0.16
    340
    +0.13
    0.09
    68
    +0.13
    0.11
    Negative Logits
    ço
    -2.00
     saline
    -1.65
     expensive
    -1.65
     contaminated
    -1.54
     poisoned
    -1.50
     honey
    -1.42
     exogenous
    -1.40
     harmful
    -1.39
     ignorance
    -1.39
     privileged
    -1.38
    POSITIVE LOGITS
     Awards
    1.81
    iversary
    1.68
     rounds
    1.60
    Chapter
    1.59
     Conference
    1.55
    ¦
    1.55
    finals
    1.52
    ĻĤ
    1.51
    bies
    1.50
    .
    1.49
    Activations Density 3.138%

    No Known Activations