© 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. 4-RES-SM
    11. 11292
    Prev
    Next
    INDEX
    Explanations

    words related to nervousness and the nervous system

    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
    343
    +0.16
    0.9%
    306
    +0.13
    0.7%
    468
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.16
    0.01
    283
    +0.13
    0.01
    253
    +0.12
    0.02
    Negative Logits
     Illumina
    -1.56
    oxacin
    -1.50
    ixel
    -1.49
    ository
    -1.48
    apshot
    -1.48
    oser
    -1.47
    estamp
    -1.43
    ameth
    -1.41
    oit
    -1.39
    shaw
    -1.38
    POSITIVE LOGITS
     system
    1.82
     disorders
    1.70
     forces
    1.48
     axis
    1.48
     atrophy
    1.47
     tract
    1.47
     regions
    1.47
     System
    1.46
     symptoms
    1.46
     cortex
    1.45
    Activations Density 0.067%

    No Known Activations