© 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. 27969
    Prev
    Next
    INDEX
    Explanations

    phrases related to structured or formal composition

    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
    56
    +0.15
    0.8%
    224
    +0.14
    0.8%
    227
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.15
    0.45
    209
    +0.14
    0.29
    402
    +0.12
    0.26
    Negative Logits
    ño
    -1.83
    ignon
    -1.78
    resp
    -1.64
    ãĤ§
    -1.57
    illac
    -1.57
    rot
    -1.55
    bery
    -1.53
    OOGLE
    -1.50
    cks
    -1.49
    ение
    -1.48
    POSITIVE LOGITS
     respectively
    1.72
     viz
    1.55
     describing
    1.54
     least
    1.54
     controlling
    1.48
     explaining
    1.48
     minimizing
    1.47
     centr
    1.41
     many
    1.40
     aids
    1.39
    Activations Density 1.554%

    No Known Activations