© 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. 31008
    Prev
    Next
    INDEX
    Explanations

    conjunctions and specific phrases related to legal or formal contexts

    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
    113
    +0.14
    0.8%
    194
    +0.12
    0.7%
    240
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.14
    0.44
    209
    +0.12
    0.30
    17
    +0.12
    0.20
    Negative Logits
    ittal
    -1.69
    č↵
    -1.55
    ^[@
    -1.52
    č↵
    -1.46
    )^[@
    -1.46
    ships
    -1.39
    smith
    -1.39
     elsewhere
    -1.37
    apers
    -1.37
    iels
    -1.34
    POSITIVE LOGITS
    «
    1.67
    ´
    1.65
    bigr
    1.63
     ”
    1.62
    duino
    1.61
    ĵ
    1.47
    Ī
    1.46
    biamo
    1.45
     excuse
    1.43
    ħ
    1.43
    Activations Density 2.552%

    No Known Activations