© 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 EvalsExportsinterp-engineNEWAPI 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. 30184
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there" in various contexts

    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
    418
    +0.17
    1.0%
    356
    +0.12
    0.7%
    333
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    85
    +0.17
    0.12
    348
    +0.12
    0.10
    65
    +0.10
    0.10
    Negative Logits
    erson
    -2.11
    agne
    -1.49
     agarose
    -1.48
    anmar
    -1.47
    erville
    -1.36
    ksen
    -1.35
    ahan
    -1.35
    ks
    -1.35
     bearings
    -1.34
    stery
    -1.33
    POSITIVE LOGITS
    forms
    1.75
    itect
    1.47
    itated
    1.45
    uds
    1.43
    ifiable
    1.42
     Respons
    1.40
    illary
    1.39
    mixed
    1.38
    itate
    1.34
    designed
    1.30
    Activations Density 0.263%

    No Known Activations