© 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. 29475
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    23
    +0.58
    4.3%
    258
    +0.24
    1.8%
    156
    +0.17
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.58
    0.08
    23
    +0.24
    0.07
    271
    +0.17
    0.03
    Negative Logits
    ÅĽci
    -2.32
    haus
    -2.02
    =”
    -1.95
    idav
    -1.92
    ista
    -1.89
    rooms
    -1.88
    room
    -1.86
    80211
    -1.86
    naire
    -1.85
    ière
    -1.84
    POSITIVE LOGITS
    then
    1.79
     sudden
    1.75
    rap
    1.70
    rapeutic
    1.65
     gentle
    1.59
     loose
    1.58
    xiety
    1.57
    ushed
    1.57
     Then
    1.56
     finally
    1.55
    Activations Density 0.071%

    No Known Activations