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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29581
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so."

    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
    74
    +0.14
    0.8%
    470
    +0.12
    0.7%
    396
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.14
    0.11
    396
    +0.12
    0.11
    64
    +0.12
    0.10
    Negative Logits
     finally
    -1.81
    sw
    -1.57
    most
    -1.52
    egen
    -1.52
     look
    -1.52
    only
    -1.50
     only
    -1.49
     indeed
    -1.48
    ies
    -1.46
    back
    -1.44
    POSITIVE LOGITS
    ½
    2.39
    ĥ½
    2.38
    ¾
    2.34
    µ
    2.20
    Ŀ
    2.19
    ³
    2.15
    Ĥ
    2.00
    §
    2.00
    ↵
    1.95
    1.95
    Activations Density 0.108%

    No Known Activations