© 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 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. 10586
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to mechanical systems and sensor technology

    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
    507
    +0.16
    0.9%
    104
    +0.12
    0.7%
    406
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    8
    +0.16
    0.02
    507
    +0.12
    0.02
    41
    +0.12
    0.04
    Negative Logits
    ¥
    -2.91
    ↵
    -2.75
    ↵↵
    -2.75
    ↵
    -2.75
    ↵↵
    -2.75
    ↵
    -2.75
    ↵↵
    -2.75
    -2.75
    -2.75
    -2.75
    POSITIVE LOGITS
     disclosed
    2.09
     thereof
    1.86
     xcex
    1.81
    xe
    1.72
     hereinafter
    1.72
     thereto
    1.63
    erably
    1.62
    impl
    1.57
     therein
    1.54
    hereinafter
    1.53
    Activations Density 0.187%

    No Known Activations