© 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. 28347
    Prev
    Next
    INDEX
    Explanations

    instances of the definite article "the"

    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
    478
    +0.21
    1.3%
    156
    +0.19
    1.1%
    98
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.21
    0.05
    98
    +0.19
    0.02
    507
    +0.18
    0.03
    Negative Logits
    "}](#
    -1.89
     aspect
    -1.52
     mixer
    -1.50
    piece
    -1.44
    etto
    -1.43
     vec
    -1.43
     version
    -1.39
     wherein
    -1.37
     corrid
    -1.37
     viscos
    -1.37
    POSITIVE LOGITS
    oretical
    2.20
    rapeutics
    2.04
     brightest
    2.02
    rapeut
    2.02
     most
    1.98
     strongest
    1.98
    rapy
    1.97
     highest
    1.92
    ses
    1.91
     same
    1.88
    Activations Density 0.621%

    No Known Activations