© 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 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. 28471
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Throughout."

    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
    296
    +0.15
    0.9%
    412
    +0.14
    0.8%
    210
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    296
    +0.15
    0.01
    59
    +0.14
    0.01
    412
    +0.12
    0.01
    Negative Logits
    ilent
    -1.89
    ĥ½
    -1.78
    ember
    -1.73
    Č
    -1.65
    endi
    -1.49
    enig
    -1.48
    ubottu
    -1.47
    yond
    -1.44
    aphragm
    -1.44
    vast
    -1.43
    POSITIVE LOGITS
    ?,
    1.55
    ?)
    1.50
     flags
    1.46
     cycling
    1.39
     mM
    1.35
     text
    1.34
     media
    1.28
     favourite
    1.27
     then
    1.27
    cu
    1.26
    Activations Density 0.046%

    No Known Activations