© 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. 10370
    Prev
    Next
    INDEX
    Explanations

    phrases that convey gratitude or appreciation

    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
    369
    +0.14
    0.8%
    205
    +0.14
    0.8%
    436
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.14
    0.01
    436
    +0.14
    0.03
    374
    +0.14
    0.02
    Negative Logits
    quo
    -1.78
     honour
    -1.59
    proj
    -1.57
     macro
    -1.48
    [@
    -1.48
     pride
    -1.45
    AML
    -1.43
    olk
    -1.43
    ={
    -1.39
    ,[@
    -1.39
    POSITIVE LOGITS
     parked
    2.24
     flashes
    1.66
     Minutes
    1.60
     minutes
    1.57
    eanor
    1.53
     asleep
    1.47
     videot
    1.45
    minutes
    1.45
     cameras
    1.39
     logs
    1.39
    Activations Density 0.753%

    No Known Activations