© 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 EvalsExportsinterp-engineNEWAPI 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. 25963
    Prev
    Next
    INDEX
    Explanations

    references to the term "MA" which could relate to multiple contexts, such as Master of Arts or Mixed Martial Arts

    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
    457
    +0.13
    0.8%
    392
    +0.11
    0.7%
    130
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.13
    0.02
    130
    +0.11
    0.02
    457
    +0.11
    0.02
    Negative Logits
     forgotten
    -1.86
     supposed
    -1.79
     answered
    -1.71
    hentic
    -1.70
     deceased
    -1.68
     slightest
    -1.67
    omitempty
    -1.67
    otted
    -1.66
     wounded
    -1.58
     mistaken
    -1.56
    POSITIVE LOGITS
    ware
    1.86
    CRO
    1.75
    ruptcy
    1.72
    plots
    1.64
    works
    1.63
    eson
    1.63
    asone
    1.63
    istry
    1.63
    ulator
    1.63
    KES
    1.62
    Activations Density 0.156%

    No Known Activations