© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28029
    Prev
    Next
    INDEX
    Explanations

    references to motivation

    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
    +0.21
    1.2%
    156
    +0.17
    1.0%
    46
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.21
    0.01
    46
    +0.17
    0.01
    22
    +0.13
    0.01
    Negative Logits
    ige
    -1.50
     brid
    -1.50
    isman
    -1.48
    stein
    -1.42
    ows
    -1.41
    sson
    -1.39
     Hon
    -1.36
    pert
    -1.36
    ides
    -1.34
     present
    -1.33
    POSITIVE LOGITS
     puzzles
    1.49
    erad
    1.43
    Ŀ
    1.43
     defeats
    1.42
     aren
    1.38
     errors
    1.37
    etect
    1.37
    actions
    1.37
     by
    1.36
    ely
    1.35
    Activations Density 0.013%

    No Known Activations