© 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. 4-RES-SM
    11. 14089
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to devices and machinery

    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
    21
    +0.14
    0.8%
    86
    +0.12
    0.7%
    268
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.20
    156
    +0.12
    0.16
    274
    +0.11
    0.12
    Negative Logits
    ĥ½
    -2.37
    Ł
    -2.32
    Ĺ
    -2.32
    ¹
    -2.30
    ľĵ
    -2.24
    ª
    -2.21
    º
    -2.21
    §
    -2.20
      ↵
    -2.18
    -2.17
    POSITIVE LOGITS
     apparatus
    2.17
     device
    1.93
     FIG
    1.90
     Patent
    1.90
     Electronics
    1.85
     an
    1.81
     apparatuses
    1.79
    anium
    1.74
     electronics
    1.74
     equipped
    1.69
    Activations Density 0.638%

    No Known Activations