© 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. 26494
    Prev
    Next
    INDEX
    Explanations

    expressions of inability or difficulty in completing tasks

    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
    193
    +0.11
    0.6%
    109
    +0.11
    0.6%
    445
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.11
    0.02
    185
    +0.11
    0.01
    113
    +0.10
    0.01
    Negative Logits
    ember
    -1.80
     mornings
    -1.72
    OULD
    -1.46
    kubernetes
    -1.42
     morn
    -1.41
    ETHOD
    -1.41
    woke
    -1.32
     Procedures
    -1.31
     Mobile
    -1.27
     countless
    -1.27
    POSITIVE LOGITS
    ismatic
    2.04
    gio
    1.60
    isma
    1.58
    ainties
    1.56
    iq
    1.52
    agna
    1.48
    olan
    1.48
    orus
    1.48
    documentclass
    1.46
    bod
    1.45
    Activations Density 0.559%

    No Known Activations