© 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. 31227
    Prev
    Next
    INDEX
    Explanations

    terms related to software licenses

    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
    98
    +0.13
    0.7%
    57
    +0.12
    0.6%
    214
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.13
    0.04
    57
    +0.12
    0.05
    230
    +0.11
    0.03
    Negative Logits
    TestCase
    -2.02
    while
    -1.54
    (@"
    -1.50
    orous
    -1.50
    assertEquals
    -1.49
     mattered
    -1.47
    (['
    -1.46
    itating
    -1.40
    ulous
    -1.38
    Inflater
    -1.36
    POSITIVE LOGITS
     license
    1.80
     lett
    1.71
    º
    1.71
     DISCLAIM
    1.70
    bsd
    1.64
     GPL
    1.62
    ÂĶ
    1.60
     licenses
    1.58
     waiver
    1.55
     revocation
    1.49
    Activations Density 0.427%

    No Known Activations