© 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. 30360
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "until."

    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
    202
    +0.12
    0.6%
    339
    +0.10
    0.6%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.12
    0.05
    443
    +0.10
    0.04
    455
    +0.10
    0.04
    Negative Logits
    thon
    -1.60
    urop
    -1.52
     right
    -1.51
     ruling
    -1.49
     penalty
    -1.44
     purpose
    -1.42
     questioning
    -1.39
     row
    -1.39
     punishment
    -1.38
     requirement
    -1.36
    POSITIVE LOGITS
    Īĺ
    2.08
    ®
    1.94
    ¹
    1.92
    »¿
    1.92
    Ħ
    1.92
    Ĵ
    1.91
    ª
    1.90
    ¸
    1.87
    Ĥ
    1.77
    Į
    1.72
    Activations Density 0.019%

    No Known Activations