© 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. MLP Post
    9. 2-MLP-SM
    11. 24865
    Prev
    Next
    INDEX
    Explanations

    medical conditions and related terminology

    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
    23
    +0.21
    1.2%
    111
    +0.14
    0.8%
    291
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.21
    0.04
    208
    +0.14
    0.04
    162
    +0.12
    0.05
    Negative Logits
    ķ
    -2.75
    ļ
    -2.68
    Į
    -2.47
    ł
    -2.43
    Ŀ
    -2.41
    ı
    -2.38
    ij
    -2.32
    Ĭ
    -2.29
    İ
    -2.28
    IJ
    -2.21
    POSITIVE LOGITS
    "}](#
    1.55
     relaxed
    1.52
    `)
    1.50
     straight
    1.49
     zip
    1.46
     encrypted
    1.42
    ']))
    1.39
    orems
    1.37
     easiest
    1.37
     accent
    1.37
    Activations Density 0.300%

    No Known Activations