© 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. 30650
    Prev
    Next
    INDEX
    Explanations

    the term "main" as a primary focus or theme in the context of various topics

    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
    438
    +0.13
    0.7%
    405
    +0.12
    0.7%
    127
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.13
    0.04
    405
    +0.12
    0.04
    3
    +0.12
    0.03
    Negative Logits
    ť
    -1.76
    olu
    -1.72
    eps
    -1.70
     ]{}
    -1.62
    webkit
    -1.59
    UTC
    -1.59
    mosp
    -1.57
    epid
    -1.56
    formaldehyde
    -1.55
    CoV
    -1.51
    POSITIVE LOGITS
    stay
    2.48
    doms
    2.07
    Īĺ
    1.91
    stro
    1.68
     ram
    1.67
    sters
    1.66
    sheet
    1.64
    ĨĴ
    1.60
    frames
    1.60
    ģ
    1.57
    Activations Density 0.383%

    No Known Activations