© 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. 30416
    Prev
    Next
    INDEX
    Explanations

    references to various types of clothing, particularly shirts

    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
    +0.20
    1.1%
    315
    +0.11
    0.6%
    99
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.20
    0.02
    506
    +0.11
    0.02
    156
    +0.10
    0.02
    Negative Logits
    ĵ
    -2.84
    ĨĴ
    -2.80
    ĥ
    -2.66
    -2.54
    -2.54
    ↵
    -2.54
    -2.54
    -2.54
    ↵
    -2.54
    č↵
    -2.54
    POSITIVE LOGITS
    nam
    2.11
    width
    1.91
    ahead
    1.89
    backed
    1.85
    written
    1.79
    length
    1.74
    ball
    1.71
    wood
    1.71
    forward
    1.68
    leneck
    1.68
    Activations Density 0.056%

    No Known Activations