© 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. 28553
    Prev
    Next
    INDEX
    Explanations

    instances of the word "oto"

    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
    376
    +0.16
    0.9%
    36
    +0.11
    0.6%
    283
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.16
    0.01
    207
    +0.11
    0.01
    283
    +0.11
    0.01
    Negative Logits
    '?"
    -1.63
    UTE
    -1.62
    soever
    -1.56
     '</
    -1.55
    '">
    -1.51
    rians
    -1.49
     APPEALS
    -1.48
     ?"
    -1.47
     others
    -1.46
     silence
    -1.46
    POSITIVE LOGITS
    enos
    2.09
    eries
    2.04
    ÅĽci
    2.02
    ÅĦ
    2.00
    istical
    1.99
    ery
    1.71
    emaker
    1.69
    pad
    1.66
    kat
    1.63
    ÅĽÄĩ
    1.59
    Activations Density 0.011%

    No Known Activations