© 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. 26639
    Prev
    Next
    INDEX
    Explanations

    references to "normal" health conditions

    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
    156
    +0.13
    0.7%
    13
    +0.12
    0.7%
    253
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.13
    0.02
    18
    +0.12
    0.01
    505
    +0.11
    0.02
    Negative Logits
    athon
    -1.84
     devoted
    -1.52
     cref
    -1.51
    ophe
    -1.50
    encial
    -1.41
    lot
    -1.31
    ready
    -1.29
    lio
    -1.28
    anol
    -1.27
    eson
    -1.27
    POSITIVE LOGITS
    izing
    2.47
    ised
    2.39
    izes
    2.27
    ise
    2.11
    ising
    2.10
    izability
    1.96
    ized
    1.89
    ize
    1.87
    isations
    1.86
    ities
    1.85
    Activations Density 0.043%

    No Known Activations