© 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. 25952
    Prev
    Next
    INDEX
    Explanations

    occurrences 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
    410
    +0.14
    0.8%
    303
    +0.13
    0.7%
    385
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.14
    0.05
    281
    +0.13
    0.05
    55
    +0.12
    0.05
    Negative Logits
    ¸
    -2.82
    ľ
    -2.80
    Ŀ
    -2.75
    ĩ
    -2.64
    ł
    -2.59
    Ĺ
    -2.57
    č↵č↵
    -2.56
    -2.56
     ↵
    -2.56
    ↵
    -2.56
    POSITIVE LOGITS
    oles
    1.79
    ellers
    1.78
    unnumbered
    1.68
    ells
    1.67
    ientes
    1.66
    ensing
    1.64
    itars
    1.64
    ãĥ¼ãĥĪ
    1.57
    eller
    1.55
    rief
    1.53
    Activations Density 0.063%

    No Known Activations