© 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. 31646
    Prev
    Next
    INDEX
    Explanations

    the notion of exceptions or exclusions in various contexts

    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
    274
    +0.17
    0.9%
    478
    +0.16
    0.9%
    115
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.17
    0.03
    335
    +0.16
    0.02
    91
    +0.10
    0.02
    Negative Logits
    ---|
    -1.57
    ust
    -1.56
     Technologies
    -1.55
    ---|---
    -1.54
    "?"
    -1.54
    ---|---|---
    -1.53
    ,'"
    -1.52
    STEM
    -1.49
    emis
    -1.48
    's
    -1.45
    POSITIVE LOGITS
    2.94
    2.94
    2.94
    2.94
    ↵
    2.94
    ↵
    2.94
    ↵
    2.94
    ↵
    2.94
    2.94
          ↵
    2.94
    Activations Density 0.109%

    No Known Activations