© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-SM
    11. 12250
    Prev
    Next
    INDEX
    Explanations

    statistics related to football games and player performances

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    105
    +0.12
    0.6%
    285
    +0.10
    0.6%
    306
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.12
    0.15
    285
    +0.10
    0.15
    319
    +0.10
    0.10
    Negative Logits
     Tibet
    -2.08
     realised
    -2.06
     labour
    -2.01
     characterised
    -2.00
     Tibetan
    -1.93
     paintings
    -1.93
     Nepal
    -1.93
     arte
    -1.89
     Buddha
    -1.88
     realise
    -1.88
    POSITIVE LOGITS
     NFL
    4.26
     quarterback
    4.15
     QB
    3.54
     linebacker
    3.52
     offseason
    3.52
     ESPN
    3.38
     preseason
    3.32
     lineback
    3.21
     Steelers
    3.11
     NCAA
    3.00
    Activations Density 2.217%

    No Known Activations