© 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. 26964
    Prev
    Next
    INDEX
    Explanations

    terminology related to logistics and supply chains

    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
    320
    +0.19
    1.1%
    47
    +0.17
    1.0%
    57
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.19
    0.11
    320
    +0.17
    0.11
    479
    +0.15
    0.04
    Negative Logits
    ĻĤ
    -1.88
     okay
    -1.66
     goodbye
    -1.63
    ¿½
    -1.60
    .’”
    -1.56
     alright
    -1.55
     aisle
    -1.52
     ok
    -1.48
     siblings
    -1.46
    ħ
    -1.45
    POSITIVE LOGITS
    ural
    1.71
    imetry
    1.46
    molecular
    1.41
    vation
    1.40
    ibility
    1.39
     underlying
    1.38
    organisms
    1.37
    acial
    1.36
    asio
    1.36
    erce
    1.35
    Activations Density 3.861%

    No Known Activations