© 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. 2-MLP-SM
    6. 25518
    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    509
    +0.12
    0.7%
    406
    +0.10
    0.6%
    502
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.12
    0.06
    502
    +0.10
    0.09
    262
    +0.10
    0.06
    Negative Logits
    ĸ
    -2.02
     slightest
    -1.75
    ħ
    -1.75
    ĸ´
    -1.72
     participants
    -1.71
    Ľ
    -1.61
    ·¸
    -1.59
     responses
    -1.57
    Ļ
    -1.56
     guests
    -1.55
    POSITIVE LOGITS
    iNdEx
    1.86
    kip
    1.83
    hin
    1.77
    usepackage
    1.75
    IEEE
    1.74
    smallmatrix
    1.66
    supplementary
    1.51
    heet
    1.50
    bmatrix
    1.50
    ="-
    1.46
    Activations Density 0.745%

    No Known Activations