© 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. 22751
    Prev
    Next
    INDEX
    Explanations

    variations of the word "tr"

    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
    156
    +0.26
    1.5%
    23
    +0.15
    0.9%
    384
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.26
    0.03
    501
    +0.15
    0.02
    316
    +0.12
    0.02
    Negative Logits
    heet
    -1.64
    heets
    -1.58
    arios
    -1.54
    ocarcin
    -1.47
    eten
    -1.45
    FIL
    -1.45
     County
    -1.45
    ygen
    -1.41
    ibi
    -1.40
    chts
    -1.39
    POSITIVE LOGITS
    dling
    1.60
     suture
    1.57
     shutdown
    1.47
     vortex
    1.41
     motions
    1.40
    acing
    1.37
     mess
    1.32
    ŀ
    1.32
    times
    1.31
     ischemia
    1.30
    Activations Density 0.110%

    No Known Activations