© 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. 0-MLP-SM
    11. 28776
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "malignant" in various contexts related to tumors or cancer

    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
    +0.29
    1.7%
    376
    +0.17
    1.0%
    340
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    340
    +0.29
    0.01
    266
    +0.17
    0.01
    339
    +0.12
    0.01
    Negative Logits
    hing
    -1.43
     complete
    -1.36
    AML
    -1.35
    llo
    -1.35
    ffen
    -1.34
    clusive
    -1.31
     Available
    -1.30
    ls
    -1.29
    lla
    -1.28
     detailed
    -1.27
    POSITIVE LOGITS
    ĻĤ
    2.33
    ¤
    2.00
    Ļª
    1.97
    £
    1.86
    °
    1.83
    µ
    1.77
    ±
    1.72
    ¼
    1.69
    Ł
    1.66
    ¸
    1.66
    Activations Density 0.008%

    No Known Activations