© 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. MLP Post
    9. 2-MLP-SM
    11. 23315
    Prev
    Next
    INDEX
    Explanations

    terms associated with health-related issues and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    209
    +0.12
    0.7%
    29
    +0.12
    0.7%
    478
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.10
    332
    +0.12
    0.09
    374
    +0.12
    0.02
    Negative Logits
    ĥ½
    -2.61
    Ļ
    -2.48
    §
    -2.39
    ²
    -2.35
    ¢
    -2.30
    Ļª
    -2.28
    Ĥ
    -2.26
    ģ
    -2.22
    ¯
    -2.22
    Ĵ
    -2.17
    POSITIVE LOGITS
     quotations
    1.62
    esto
    1.48
     excerpt
    1.39
    documentclass
    1.39
     df
    1.38
     HREF
    1.37
     plot
    1.37
     rectangular
    1.37
     explanation
    1.36
    umber
    1.36
    Activations Density 1.845%

    No Known Activations