© 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 EvalsExportsAPI 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. 28809
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Editor."

    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
    410
    +0.12
    0.7%
    376
    +0.11
    0.7%
    336
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.12
    0.01
    336
    +0.11
    0.01
    398
    +0.10
    0.01
    Negative Logits
    omers
    -1.58
    abouts
    -1.55
    between
    -1.50
     cross
    -1.50
     CDC
    -1.47
     longer
    -1.46
    eing
    -1.45
     survivor
    -1.45
      ↵
    -1.44
    ameth
    -1.38
    POSITIVE LOGITS
    ial
    2.46
    ¾
    2.12
    ious
    1.96
    ials
    1.88
    ios
    1.81
     owes
    1.76
    ÃŃa
    1.73
    ium
    1.72
    iously
    1.69
    ieux
    1.69
    Activations Density 0.225%

    No Known Activations