© 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. 29285
    Prev
    Next
    INDEX
    Explanations

    mentions of preparations for events or activities

    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
    156
    +0.22
    1.3%
    376
    +0.11
    0.6%
    365
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.22
    0.01
    319
    +0.11
    0.01
    156
    +0.10
    0.01
    Negative Logits
    ĥ½
    -3.20
    į
    -2.80
    ĸ´
    -2.73
    ĵ
    -2.71
    §
    -2.63
    ĭ
    -2.61
    ľĵ
    -2.55
    ľ
    -2.54
    Ń
    -2.52
    Ĵ
    -2.50
    POSITIVE LOGITS
    iative
    1.99
    hell
    1.93
    imate
    1.78
    apsed
    1.72
    iform
    1.63
    imal
    1.61
    etable
    1.56
    ional
    1.54
    istine
    1.51
    iment
    1.48
    Activations Density 0.015%

    No Known Activations