© 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. 28250
    Prev
    Next
    INDEX
    Explanations

    mentions of poetry and poetic formats

    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
    +0.33
    1.9%
    38
    +0.11
    0.7%
    479
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.33
    0.01
    511
    +0.11
    0.01
    365
    +0.10
    0.01
    Negative Logits
     ages
    -1.84
     who
    -1.48
    )$-
    -1.44
     eternity
    -1.43
    onas
    -1.37
    ĥ½
    -1.35
    ott
    -1.34
    ostatic
    -1.34
    utting
    -1.32
    woke
    -1.29
    POSITIVE LOGITS
    strings
    1.70
    birds
    1.54
    ily
    1.53
    fully
    1.51
    ful
    1.45
    plate
    1.43
    fish
    1.42
    writers
    1.41
    istically
    1.38
    ong
    1.38
    Activations Density 0.031%

    No Known Activations