© 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. 25772
    Prev
    Next
    INDEX
    Explanations

    user interface elements

    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
    392
    +0.13
    0.8%
    376
    +0.12
    0.7%
    410
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.13
    0.02
    344
    +0.12
    0.02
    162
    +0.11
    0.02
    Negative Logits
     Ski
    -1.66
     true
    -1.49
     ')
    -1.47
     ?"
    -1.46
     '')
    -1.46
     Sleep
    -1.45
     same
    -1.45
      ↵
    -1.43
    swers
    -1.39
     MERCHANTABILITY
    -1.39
    POSITIVE LOGITS
    etable
    1.89
    cias
    1.82
    recht
    1.78
    eto
    1.78
    quist
    1.74
    judicial
    1.74
    âĢIJ
    1.72
    year
    1.71
    liga
    1.65
    ÅĨ
    1.62
    Activations Density 0.020%

    No Known Activations