© 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. 13073
    Prev
    Next
    INDEX
    Explanations

    references to hip-related medical conditions and surgeries

    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
    362
    +0.12
    0.7%
    312
    +0.11
    0.6%
    309
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    309
    +0.12
    0.03
    153
    +0.11
    0.03
    202
    +0.11
    0.01
    Negative Logits
    ificance
    -1.98
    ptions
    -1.92
    idge
    -1.89
    naments
    -1.86
    isons
    -1.84
    ials
    -1.82
    imals
    -1.73
    ial
    -1.70
    unds
    -1.66
    ially
    -1.66
    POSITIVE LOGITS
    ĻĤ
    2.38
     arthro
    2.36
     joints
    2.12
    Į
    2.08
    Ĭ
    2.02
     replacement
    1.97
     arthritis
    1.94
    ²
    1.90
    opan
    1.90
     replacements
    1.87
    Activations Density 0.173%

    No Known Activations