© 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. 29610
    Prev
    Next
    INDEX
    Explanations

    the use of the word "To."

    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
    372
    +0.12
    0.7%
    245
    +0.11
    0.6%
    152
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.12
    0.04
    431
    +0.11
    0.03
    300
    +0.11
    0.03
    Negative Logits
     exemptions
    -1.51
    pone
    -1.46
     advice
    -1.43
    fax
    -1.42
     anonymity
    -1.40
     unsupported
    -1.39
     immunity
    -1.36
    unreadable
    -1.35
     eggs
    -1.35
     extensions
    -1.35
    POSITIVE LOGITS
     below
    1.87
    ometh
    1.64
    shire
    1.46
     mean
    1.46
    hesis
    1.45
    eenth
    1.42
     showed
    1.41
    upe
    1.40
    ington
    1.38
    asek
    1.33
    Activations Density 0.019%

    No Known Activations