© 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. 27988
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this."

    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
    113
    +0.15
    0.9%
    71
    +0.14
    0.8%
    56
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.15
    0.15
    26
    +0.14
    0.14
    199
    +0.11
    0.14
    Negative Logits
    worthy
    -1.56
     Ara
    -1.37
    /
    -1.36
    :&
    -1.35
    rs
    -1.32
     exacerb
    -1.32
    ring
    -1.29
     Schr
    -1.29
     reflections
    -1.28
    ms
    -1.27
    POSITIVE LOGITS
    zen
    1.67
    tron
    1.63
    ussy
    1.58
    db
    1.58
    ked
    1.54
    ginx
    1.53
    lion
    1.52
    ku
    1.48
    nement
    1.46
    ixel
    1.46
    Activations Density 0.273%

    No Known Activations