© 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. 28680
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "un" used as a prefix or standalone word

    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
    59
    +0.15
    0.8%
    369
    +0.14
    0.8%
    377
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    439
    +0.15
    0.03
    240
    +0.14
    0.03
    59
    +0.14
    0.02
    Negative Logits
     Ethics
    -1.56
     separate
    -1.40
    unnumbered
    -1.39
     false
    -1.36
    ETHOD
    -1.34
     obstruction
    -1.33
     False
    -1.33
    protobuf
    -1.32
    IRS
    -1.30
     respective
    -1.29
    POSITIVE LOGITS
    ½
    2.31
    µ
    2.26
    Ĭ
    2.09
    ¬
    2.07
    Īĺ
    2.02
    Ĵ
    2.02
    ©
    2.01
    ĻĤ
    1.95
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    1.95
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    1.95
    Activations Density 0.202%

    No Known Activations