© 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. 2-MLP-SM
    11. 22992
    Prev
    Next
    INDEX
    Explanations

    transformations of the word "et" and related phrases

    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
    451
    +0.14
    0.8%
    11
    +0.12
    0.7%
    303
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.14
    0.07
    222
    +0.12
    0.05
    491
    +0.12
    0.03
    Negative Logits
    ":{
    -1.77
    ">
    -1.73
     spans
    -1.51
    .</
    -1.50
    rival
    -1.50
    versus
    -1.49
    rient
    -1.48
    "><
    -1.48
     spanned
    -1.47
    racted
    -1.47
    POSITIVE LOGITS
     pity
    1.54
     grub
    1.46
    idently
    1.38
     ventilation
    1.38
    iously
    1.32
     inferences
    1.30
     Rs
    1.27
     boot
    1.27
     argu
    1.26
     relief
    1.26
    Activations Density 2.375%

    No Known Activations