© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31048
    Prev
    Next
    INDEX
    Explanations

    instances of the word "appear" in various forms

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    84
    +0.12
    0.7%
    508
    +0.11
    0.7%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    84
    +0.12
    0.01
    111
    +0.11
    0.01
    508
    +0.11
    0.01
    Negative Logits
    Ĭ
    -1.88
    ĥ½
    -1.75
    \)
    -1.64
    anus
    -1.56
    anian
    -1.54
      ↵
    -1.53
    ĵ
    -1.44
    ronic
    -1.43
    ľĵ
    -1.43
    ndef
    -1.42
    POSITIVE LOGITS
    ÅĽci
    1.82
    als
    1.82
    ary
    1.59
    fields
    1.58
    ctions
    1.55
    ÑĤе
    1.54
    aires
    1.52
    hole
    1.51
    ographies
    1.50
    ÅĽÄĩ
    1.50
    Activations Density 0.019%

    No Known Activations