© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27942
    Prev
    Next
    INDEX
    Explanations

    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
    246
    +0.12
    0.7%
    212
    +0.12
    0.7%
    461
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.12
    0.48
    98
    +0.12
    0.21
    228
    +0.11
    0.32
    Negative Logits
    ĥ½
    -1.86
    ĵ
    -1.70
    CTYPE
    -1.48
    ¡
    -1.44
    ¦
    -1.40
     transit
    -1.36
    į
    -1.36
    vity
    -1.33
     spacecraft
    -1.33
     bowel
    -1.32
    POSITIVE LOGITS
    ourse
    1.56
    elf
    1.50
    ?).
    1.48
    =\{
    1.47
    =.
    1.46
     them
    1.45
    egen
    1.43
    leading
    1.41
    empty
    1.39
    iken
    1.39
    Activations Density 2.894%

    No Known Activations