© 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. 2-RES-SM
    11. 9806
    Prev
    Next
    INDEX
    Explanations

    references to sports coaching and coaching-related roles

    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%
    471
    +0.15
    0.9%
    365
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.23
    0.02
    365
    +0.15
    0.03
    128
    +0.14
    0.02
    Negative Logits
    ĥ½
    -1.64
    ){#
    -1.51
    apine
    -1.50
     supra
    -1.47
    anus
    -1.46
    amil
    -1.45
    akk
    -1.41
    pto
    -1.40
     parcel
    -1.38
    û
    -1.37
    POSITIVE LOGITS
    manager
    1.87
     manager
    1.86
    ship
    1.86
    manship
    1.75
    yard
    1.69
     controls
    1.67
    visor
    1.65
    ery
    1.63
    staff
    1.63
    wright
    1.62
    Activations Density 0.176%

    No Known Activations