© 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. 25476
    Prev
    Next
    INDEX
    Explanations

    keywords related to metrics and performance evaluations in business contexts

    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
    47
    +0.16
    0.9%
    192
    +0.12
    0.7%
    107
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.16
    0.01
    10
    +0.12
    0.03
    98
    +0.12
    -0.01
    Negative Logits
     itself
    -1.78
    ?_
    -1.56
    oster
    -1.56
     preced
    -1.48
    erior
    -1.47
     orbital
    -1.47
     expires
    -1.46
     aliqu
    -1.42
    decre
    -1.42
    ului
    -1.41
    POSITIVE LOGITS
    wn
    1.52
    kay
    1.49
    aney
    1.47
    ories
    1.44
    ki
    1.44
     whole
    1.39
    kas
    1.37
     wherever
    1.33
     ----,
    1.32
    chs
    1.29
    Activations Density 0.602%

    No Known Activations