© 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. 1-RES-SM
    11. 26016
    Prev
    Next
    INDEX
    Explanations

    mentions of specific criteria or criteria-related terms that involve standards or prerequisites across 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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    376
    +0.16
    0.9%
    365
    +0.16
    0.9%
    156
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.16
    0.03
    38
    +0.16
    0.02
    126
    +0.13
    0.02
    Negative Logits
    Ĵ
    -3.88
    ¾
    -3.52
    ¿½
    -3.40
    §
    -3.39
    ĥ½
    -3.36
      ↵
    -3.19
    -3.19
    ↵↵
    -3.19
    -3.19
    -3.19
    POSITIVE LOGITS
     required
    1.88
    frame
    1.69
    etting
    1.69
     ignition
    1.60
     regulating
    1.57
    documentclass
    1.56
    ivated
    1.56
    header
    1.54
     compliance
    1.50
     adjust
    1.49
    Activations Density 0.108%

    No Known Activations