© 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. 27134
    Prev
    Next
    INDEX
    Explanations

    references to guest contributions or guest posts

    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
    +0.16
    0.9%
    156
    +0.15
    0.8%
    450
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.16
    0.01
    24
    +0.15
    0.01
    483
    +0.11
    0.01
    Negative Logits
     rest
    -1.65
     whit
    -1.64
     blocks
    -1.62
     sleeve
    -1.57
     proven
    -1.50
     heels
    -1.48
    ching
    -1.48
     shame
    -1.47
     cholesterol
    -1.47
     brow
    -1.46
    POSITIVE LOGITS
    doms
    1.75
    "}](#
    1.74
    hill
    1.69
    walk
    1.67
    boat
    1.66
    writers
    1.63
    quart
    1.62
    olini
    1.57
    piece
    1.57
    RUPT
    1.57
    Activations Density 0.014%

    No Known Activations