© 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. 26678
    Prev
    Next
    INDEX
    Explanations

    references to the concept of something being "new."

    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
    436
    +0.17
    0.9%
    156
    +0.16
    0.9%
    193
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.17
    0.02
    436
    +0.16
    0.03
    50
    +0.11
    0.03
    Negative Logits
    ople
    -1.95
    ose
    -1.79
    ám
    -1.70
    inib
    -1.65
    oglobin
    -1.64
    asek
    -1.64
    aches
    -1.64
    ysis
    -1.61
    yses
    -1.61
    aca
    -1.61
    POSITIVE LOGITS
    bie
    2.41
    stalk
    2.00
    found
    1.92
    tons
    1.91
    lines
    1.85
    bies
    1.80
    castle
    1.74
     versions
    1.73
     horiz
    1.73
     Zealand
    1.70
    Activations Density 0.097%

    No Known Activations