© 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. 2-RES-SM
    11. 31392
    Prev
    Next
    INDEX
    Explanations

    elements related to legal case references and motions

    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
    263
    +0.22
    1.3%
    369
    +0.12
    0.7%
    190
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.22
    0.12
    263
    +0.12
    0.15
    190
    +0.11
    0.15
    Negative Logits
    ¿½
    -3.04
    §
    -2.10
    į
    -1.99
    Ħ
    -1.97
    ģ
    -1.94
    Ĩ
    -1.92
    Ń
    -1.89
    ĻĤ
    -1.88
    ŀ
    -1.83
    Ĺ
    -1.82
    POSITIVE LOGITS
    lessly
    1.64
    falls
    1.62
    >(
    1.58
     checkbox
    1.49
     temptation
    1.49
     benefit
    1.49
     sparing
    1.46
     sake
    1.43
    drop
    1.38
     validation
    1.34
    Activations Density 4.390%

    No Known Activations