© 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. 24973
    Prev
    Next
    INDEX
    Explanations

    instances of the word "form."

    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
    49
    +0.12
    0.7%
    286
    +0.11
    0.6%
    441
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.12
    0.01
    441
    +0.11
    0.01
    378
    +0.11
    0.01
    Negative Logits
    OOGLE
    -1.68
    ravel
    -1.54
    ureus
    -1.47
    opic
    -1.44
    UGH
    -1.44
     ")
    -1.41
    unnel
    -1.41
    ope
    -1.38
     knees
    -1.36
    openh
    -1.35
    POSITIVE LOGITS
    ĻĤ
    1.87
    ģ
    1.84
    enos
    1.75
    emente
    1.70
    ©
    1.55
    fest
    1.52
     ethic
    1.50
    ics
    1.50
     recurs
    1.47
    enstein
    1.46
    Activations Density 0.034%

    No Known Activations