© 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. 25454
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "mass" in various contexts

    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
    336
    +0.14
    0.8%
    376
    +0.12
    0.7%
    135
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    336
    +0.14
    0.02
    120
    +0.12
    0.01
    135
    +0.10
    0.02
    Negative Logits
    iances
    -1.75
    scriptions
    -1.74
    aliana
    -1.71
    ften
    -1.63
    woke
    -1.62
    respectively
    -1.53
    ĥ
    -1.52
    prevent
    -1.52
    TRODUCTION
    -1.52
     Hillary
    -1.50
    POSITIVE LOGITS
    achusetts
    2.53
     spectrometry
    2.28
    "}](#
    1.96
     spectrometer
    1.83
    ARRAY
    1.79
     analyzer
    1.63
    borough
    1.63
    iles
    1.61
    gap
    1.60
    plate
    1.58
    Activations Density 0.076%

    No Known Activations