© 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. 25462
    Prev
    Next
    INDEX
    Explanations

    references to errors and mistakes in a legal context

    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
    376
    +0.14
    0.8%
    412
    +0.13
    0.8%
    235
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.14
    0.01
    375
    +0.13
    0.01
    322
    +0.13
    0.01
    Negative Logits
    Č
    -1.76
     @
    -1.54
    www
    -1.50
    ilities
    -1.45
     questioned
    -1.45
     probed
    -1.41
     traced
    -1.40
    eras
    -1.40
     around
    -1.38
     muscles
    -1.37
    POSITIVE LOGITS
     era
    2.07
    âĢIJ
    1.64
    anks
    1.63
     Era
    1.42
     ave
    1.41
     arsenal
    1.40
    Ä
    1.39
    igue
    1.38
    ÅĽÄĩ
    1.38
    istry
    1.37
    Activations Density 0.468%

    No Known Activations