© 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. 26135
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "works."

    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
    +0.13
    0.8%
    260
    +0.13
    0.8%
    388
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.13
    0.01
    388
    +0.13
    0.01
    363
    +0.11
    0.01
    Negative Logits
     suppose
    -1.81
    bey
    -1.67
     shame
    -1.65
     ashamed
    -1.62
    woke
    -1.55
     certain
    -1.44
    'll
    -1.42
    'm
    -1.41
     mismo
    -1.39
    aning
    -1.36
    POSITIVE LOGITS
    pace
    2.57
    hops
    2.35
    bench
    2.35
    manship
    2.27
    hop
    2.24
    heet
    2.20
    station
    2.09
    piece
    2.07
    grounds
    2.06
    pieces
    1.99
    Activations Density 0.005%

    No Known Activations