© 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. 30737
    Prev
    Next
    INDEX
    Explanations

    the word "capture" in various forms, indicating an emphasis on the act of capturing moments or images

    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
    +0.20
    1.2%
    156
    +0.18
    1.0%
    148
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.20
    0.02
    474
    +0.18
    0.01
    9
    +0.16
    0.01
    Negative Logits
    npmjs
    -1.74
    unnumbered
    -1.66
    "}](#
    -1.57
    microorganisms
    -1.55
    documentclass
    -1.53
    roller
    -1.52
    ros
    -1.51
    DN
    -1.47
    AY
    -1.46
    fasterxml
    -1.46
    POSITIVE LOGITS
     footage
    2.11
     details
    2.02
     detail
    1.96
     images
    1.82
     sight
    1.79
     scenes
    1.75
     clips
    1.72
     instance
    1.64
     accuracy
    1.63
     imagery
    1.60
    Activations Density 0.023%

    No Known Activations