© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 26882
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Found"

    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
    +0.17
    1.0%
    376
    +0.14
    0.8%
    334
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.17
    0.01
    118
    +0.14
    0.01
    439
    +0.14
    0.01
    Negative Logits
     same
    -1.75
    ?”
    -1.68
     discharged
    -1.50
     night
    -1.43
     gone
    -1.41
    aning
    -1.41
    ights
    -1.37
     #{
    -1.35
    ashing
    -1.33
    ãĤĥ
    -1.32
    POSITIVE LOGITS
    iffe
    1.76
    onium
    1.42
    gio
    1.42
    ^[@
    1.41
    urther
    1.38
    rations
    1.36
    adel
    1.34
    icia
    1.33
    minent
    1.33
    amsbsy
    1.32
    Activations Density 0.027%

    No Known Activations