© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-MLP-SM
    11. 26953
    Prev
    Next
    INDEX
    Explanations

    terms related to surgical procedures and medical assessments

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.17
    1.0%
    71
    +0.14
    0.8%
    237
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.17
    0.01
    242
    +0.14
    0.01
    237
    +0.13
    0.01
    Negative Logits
    ¿½
    -2.58
    Ī
    -2.57
    IJ
    -2.56
    Ķ
    -2.52
    ↵
    -2.47
    č↵
    -2.47
     ↵
    -2.47
    -2.47
    ↵            ↵
    -2.47
    -2.47
    POSITIVE LOGITS
    erior
    1.60
    prises
    1.48
    sis
    1.46
     relativity
    1.42
    genstein
    1.42
    bud
    1.39
    ske
    1.39
    ptions
    1.39
     aperture
    1.38
    gang
    1.36
    Activations Density 0.011%

    No Known Activations