© 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. 26803
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court cases

    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
    72
    +0.15
    0.8%
    410
    +0.14
    0.8%
    65
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    65
    +0.15
    0.04
    18
    +0.14
    0.03
    374
    +0.13
    0.03
    Negative Logits
    []{
    -1.98
     <-
    -1.45
     %
    -1.45
     gold
    -1.45
     upside
    -1.42
    .[]{
    -1.39
     basics
    -1.39
     intact
    -1.38
     limitation
    -1.37
     trillion
    -1.36
    POSITIVE LOGITS
    ĥ
    3.26
    İ
    3.16
    ¤
    3.14
    ĥ½
    3.08
    ¹
    3.07
    ĵ
    3.06
    ŀ
    3.03
    ¸
    2.98
    º
    2.96
    ±
    2.95
    Activations Density 0.094%

    No Known Activations