© 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. 26757
    Prev
    Next
    INDEX
    Explanations

    the article "an" in various contexts throughout the text

    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
    23
    +0.22
    1.3%
    478
    +0.18
    1.0%
    98
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.22
    0.09
    98
    +0.18
    0.05
    281
    +0.15
    0.09
    Negative Logits
    ÅĽci
    -1.81
    ÅĽÄĩ
    -1.73
     apparatus
    -1.72
    nolimits
    -1.58
    RPC
    -1.56
     ceil
    -1.55
     Rapids
    -1.55
     finances
    -1.55
    ÃŃa
    -1.49
    ами
    -1.44
    POSITIVE LOGITS
     longer
    1.82
     thousand
    1.81
     hundred
    1.80
     dozen
    1.76
     harder
    1.75
    onym
    1.69
     few
    1.64
    cknowled
    1.62
     mighty
    1.60
     wider
    1.60
    Activations Density 7.752%

    No Known Activations