© 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. 26554
    Prev
    Next
    INDEX
    Explanations

    instances of the term "network" related to technology and infrastructure

    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
    156
    +0.23
    1.3%
    244
    +0.12
    0.7%
    172
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.23
    0.02
    451
    +0.12
    0.01
    230
    +0.11
    0.01
    Negative Logits
    inine
    -1.63
     cref
    -1.57
    hift
    -1.52
     preventive
    -1.51
     sue
    -1.50
     little
    -1.49
     decir
    -1.48
     drastic
    -1.46
     stringent
    -1.46
     miscar
    -1.46
    POSITIVE LOGITS
    atics
    2.42
    ed
    1.95
    atization
    1.92
     infrastructure
    1.88
    atically
    1.82
     overhead
    1.78
    atic
    1.72
     topology
    1.70
    works
    1.68
    stalk
    1.66
    Activations Density 0.085%

    No Known Activations