© 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. 28200
    Prev
    Next
    INDEX
    Explanations

    critical opinions about sports management decisions

    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
    306
    +0.12
    0.7%
    431
    +0.11
    0.6%
    210
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.12
    0.06
    341
    +0.11
    0.06
    150
    +0.10
    0.06
    Negative Logits
    glass
    -1.72
    olite
    -1.58
    schemas
    -1.49
     ppm
    -1.47
     analy
    -1.47
     labeled
    -1.45
    contains
    -1.44
    ).](
    -1.42
     ](
    -1.38
    crystall
    -1.38
    POSITIVE LOGITS
     Football
    2.14
     offseason
    2.13
     FIFA
    1.99
    Football
    1.93
     career
    1.92
     players
    1.90
     freelance
    1.89
     footballers
    1.86
     football
    1.82
    football
    1.81
    Activations Density 0.744%

    No Known Activations