© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 12493
    Prev
    Next
    INDEX
    Explanations

    various mathematical properties and relationships involving variables and their constraints

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    23
    +0.13
    0.7%
    411
    +0.11
    0.6%
    357
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.03
    357
    +0.11
    0.02
    144
    +0.10
    0.02
    Negative Logits
    ató
    -2.18
    msgid
    -1.77
    ^](#
    -1.68
     emphasis
    -1.67
    ourses
    -1.60
    gov
    -1.59
    matic
    -1.54
    management
    -1.51
     benefit
    -1.51
     offers
    -1.50
    POSITIVE LOGITS
    omorphisms
    2.35
     invertible
    2.33
     injective
    2.19
     surjective
    2.15
    omorphic
    2.08
     orthon
    2.08
     bounded
    2.05
     integers
    2.02
     nonnegative
    2.01
     differentiable
    2.00
    Activations Density 0.087%

    No Known Activations