© 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. 11936
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numbers and values associated with sports

    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
    156
    +0.24
    1.5%
    397
    +0.14
    0.8%
    340
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.24
    0.04
    320
    +0.14
    0.18
    227
    +0.12
    0.16
    Negative Logits
    ĥ½
    -3.34
    Ħ
    -3.29
    º
    -3.03
    Ģ
    -3.02
    Ł
    -2.92
    Ĵ
    -2.84
    ģ
    -2.82
    ¯
    -2.77
    č↵
    -2.76
    -2.76
    POSITIVE LOGITS
     his
    4.80
     himself
    4.50
     he
    3.99
     him
    3.79
    himself
    3.49
     His
    3.03
    his
    3.01
     He
    3.00
    His
    2.77
     hes
    2.60
    Activations Density 4.796%

    No Known Activations