© 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. 23789
    Prev
    Next
    INDEX
    Explanations

    instances of the word "let" in various contexts

    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
    23
    +0.28
    1.6%
    312
    +0.14
    0.8%
    39
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.28
    0.03
    162
    +0.14
    0.04
    312
    +0.12
    0.04
    Negative Logits
    ÃŃa
    -2.30
    ÃŃan
    -2.18
    ipers
    -1.93
    eda
    -1.88
    ÃŃvel
    -1.88
    endas
    -1.84
    elta
    -1.82
    éd
    -1.82
    ido
    -1.68
    ÅĽÄĩ
    -1.67
    POSITIVE LOGITS
     listening
    1.51
     tolerated
    1.48
     speaking
    1.46
     acting
    1.40
     shy
    1.38
    ness
    1.38
     ruling
    1.37
     frown
    1.37
    Loading
    1.36
    production
    1.36
    Activations Density 0.405%

    No Known Activations