© 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. 28066
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual

    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
    +0.18
    1.1%
    478
    +0.17
    1.0%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    96
    +0.18
    0.12
    303
    +0.17
    0.10
    191
    +0.12
    0.10
    Negative Logits
    arium
    -1.84
    table
    -1.61
    ige
    -1.58
    vier
    -1.55
     him
    -1.54
    anto
    -1.50
     where
    -1.42
    while
    -1.39
    )):
    -1.37
    frame
    -1.34
    POSITIVE LOGITS
     own
    2.71
    ses
    2.02
    sed
    1.98
    sing
    1.89
     Own
    1.88
     wife
    1.84
    elf
    1.81
    croft
    1.77
     daughter
    1.76
     daughters
    1.73
    Activations Density 3.746%

    No Known Activations