© 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. 2-MLP-SM
    11. 25396
    Prev
    Next
    INDEX
    Explanations

    terms related to tumor types, specifically focusing on "oma" and its various forms

    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
    +0.18
    1.0%
    294
    +0.13
    0.7%
    345
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.18
    0.02
    478
    +0.13
    0.03
    198
    +0.12
    0.03
    Negative Logits
    Ŀ
    -1.95
    ®
    -1.79
    Ń
    -1.71
    Ļ
    -1.71
    İ
    -1.71
    ports
    -1.67
    hot
    -1.66
    place
    -1.65
    hors
    -1.60
    ļ
    -1.58
    POSITIVE LOGITS
     teac
    1.58
     contents
    1.52
     orderly
    1.52
     CONTRIBUTORS
    1.51
    áĢº
    1.43
    .|
    1.40
     obed
    1.40
     existence
    1.37
     ../
    1.36
     greet
    1.36
    Activations Density 0.172%

    No Known Activations