© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27804
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "backing up."

    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
    439
    +0.11
    0.6%
    455
    +0.10
    0.6%
    222
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.11
    0.09
    95
    +0.10
    0.09
    399
    +0.10
    0.08
    Negative Logits
    sworth
    -1.82
    lands
    -1.78
    stro
    -1.59
    dered
    -1.59
    bery
    -1.58
    beat
    -1.54
    shire
    -1.53
    tle
    -1.49
    orious
    -1.49
    imming
    -1.49
    POSITIVE LOGITS
     interface
    1.61
     respectively
    1.61
    age
    1.59
     Soci
    1.46
    ylon
    1.45
     Discussion
    1.45
     Devices
    1.42
     Biomed
    1.42
     Convention
    1.41
     interfaces
    1.38
    Activations Density 0.108%

    No Known Activations