© 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. 24741
    Prev
    Next
    INDEX
    Explanations

    references to blogs or blogging activities

    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
    410
    +0.21
    1.2%
    156
    +0.19
    1.1%
    339
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.21
    0.04
    271
    +0.19
    0.01
    156
    +0.14
    0.03
    Negative Logits
     degree
    -1.73
     parental
    -1.69
     facult
    -1.68
     extent
    -1.63
     lim
    -1.62
     chambers
    -1.61
     certain
    -1.60
     dich
    -1.53
     spaces
    -1.52
     strict
    -1.49
    POSITIVE LOGITS
    ger
    3.09
    ging
    3.07
    gers
    2.82
    ged
    2.48
    gments
    2.40
    gins
    2.18
    estone
    2.13
    gie
    2.06
    gett
    1.97
    liament
    1.96
    Activations Density 0.272%

    No Known Activations