© 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. 2-RES-SM
    11. 10940
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to cases and parties involved in litigation

    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
    184
    +0.13
    0.7%
    181
    +0.11
    0.6%
    87
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.13
    0.02
    87
    +0.11
    0.02
    495
    +0.11
    0.02
    Negative Logits
    Ĵ
    -1.63
    casting
    -1.62
    ingale
    -1.61
    itudinal
    -1.60
     doesn
    -1.60
    ographer
    -1.58
    maker
    -1.57
    =%
    -1.54
     doesnt
    -1.53
    º
    -1.49
    POSITIVE LOGITS
    uit
    2.00
     allege
    2.00
    '
    1.92
    heet
    1.85
    uits
    1.84
     argue
    1.83
    pecific
    1.79
     claim
    1.78
    ugar
    1.73
    hift
    1.71
    Activations Density 0.115%

    No Known Activations