© 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. 28490
    Prev
    Next
    INDEX
    Explanations

    terminology related to sports performance and attributes

    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
    426
    +0.13
    0.7%
    292
    +0.12
    0.6%
    198
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.13
    0.03
    198
    +0.12
    0.01
    386
    +0.11
    0.02
    Negative Logits
     remar
    -1.52
    ffer
    -1.45
     raised
    -1.44
    zc
    -1.40
     payable
    -1.39
     toll
    -1.37
     rue
    -1.36
     phr
    -1.36
     "`
    -1.36
     cha
    -1.34
    POSITIVE LOGITS
    .[]{
    1.77
     mode
    1.75
    Ī
    1.63
    ariat
    1.58
    momentum
    1.57
    ĻĤ
    1.54
    chains
    1.53
    letons
    1.51
    ition
    1.51
     Sandy
    1.47
    Activations Density 0.323%

    No Known Activations