© 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. 25008
    Prev
    Next
    INDEX
    Explanations

    concepts related to medical treatments and outcomes

    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
    156
    +0.50
    3.2%
    34
    +0.11
    0.7%
    56
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.50
    -0.01
    56
    +0.11
    0.06
    452
    +0.10
    0.00
    Negative Logits
    ↵
    -3.27
    ↵
    -3.27
    ↵
    -3.27
    -3.27
     ↵
    -3.27
     ↵
    -3.27
    ↵  ³³³
    -3.27
    ↵↵
    -3.27
    č↵
    -3.27
    ↵↵
    -3.27
    POSITIVE LOGITS
     hire
    1.53
    imize
    1.51
    VALUE
    1.39
     budget
    1.34
     Pers
    1.28
     rpm
    1.28
     Effective
    1.28
     ENG
    1.27
     Instruments
    1.24
     instance
    1.24
    Activations Density 0.608%

    No Known Activations