© 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. 2-MLP-SM
    11. 22891
    Prev
    Next
    INDEX
    Explanations

    occurrences of the article "a" and other determiner variations in different contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    430
    +0.14
    0.8%
    270
    +0.14
    0.8%
    296
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.14
    0.07
    509
    +0.14
    0.04
    314
    +0.13
    0.05
    Negative Logits
     whichever
    -1.77
    sense
    -1.41
     Heat
    -1.40
    cutting
    -1.36
     Abe
    -1.36
     HK
    -1.34
     meaning
    -1.32
    ·
    -1.32
     Wash
    -1.31
    Applied
    -1.31
    POSITIVE LOGITS
    ographically
    1.82
    pts
    1.61
    coli
    1.57
    reon
    1.56
    ographic
    1.54
    .[^
    1.53
    bins
    1.47
    nier
    1.46
    elijk
    1.42
    enium
    1.41
    Activations Density 0.589%

    No Known Activations