© 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. 25169
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "case" in various 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
    366
    +0.11
    0.7%
    41
    +0.10
    0.6%
    469
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.11
    0.03
    55
    +0.10
    0.02
    12
    +0.09
    0.02
    Negative Logits
     thousands
    -1.64
     millions
    -1.56
    UST
    -1.51
    upon
    -1.48
     incumbent
    -1.46
    unnumbered
    -1.46
     JUD
    -1.42
    ership
    -1.41
     BGCOLOR
    -1.39
    ubottu
    -1.39
    POSITIVE LOGITS
    iones
    2.02
    ione
    1.90
    ional
    1.88
    enstein
    1.87
    iere
    1.76
    aria
    1.75
    cias
    1.70
    arial
    1.69
    ière
    1.69
    aper
    1.68
    Activations Density 0.012%

    No Known Activations