© 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. 9984
    Prev
    Next
    INDEX
    Explanations

    terms related to health conditions and medical diagnoses

    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
    156
    +0.27
    1.5%
    240
    +0.13
    0.8%
    183
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.27
    0.08
    369
    +0.13
    0.03
    350
    +0.13
    0.05
    Negative Logits
    )",
    -1.98
    "],
    -1.59
    "])
    -1.56
    "}](#
    -1.54
     )"
    -1.52
    eligible
    -1.47
    )."
    -1.46
    )',
    -1.46
    inux
    -1.45
    )"
    -1.44
    POSITIVE LOGITS
    ³
    2.38
    ·
    2.38
    »
    2.28
    ĻĤ
    2.16
    Ģ
    2.13
    ħ
    2.12
    ²
    2.11
    «
    2.05
    Ń
    2.04
    ¢
    2.04
    Activations Density 0.347%

    No Known Activations