© 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. 1-RES-SM
    11. 28522
    Prev
    Next
    INDEX
    Explanations

    references to graphical user interface components

    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
    +0.15
    0.8%
    100
    +0.12
    0.7%
    20
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.15
    0.02
    42
    +0.12
    0.02
    255
    +0.10
    0.02
    Negative Logits
     little
    -1.84
    ylase
    -1.65
     few
    -1.61
    ilities
    -1.60
     neither
    -1.59
     second
    -1.56
    woke
    -1.55
    xygen
    -1.55
    ught
    -1.54
     privileged
    -1.53
    POSITIVE LOGITS
     Caption
    2.09
    port
    2.04
    ership
    1.75
    istas
    1.74
    ista
    1.71
    acho
    1.70
    ĨĴ
    1.67
    acional
    1.64
    ister
    1.63
    ERTY
    1.62
    Activations Density 0.048%

    No Known Activations