© 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. 23619
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of."

    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
    510
    +0.15
    0.8%
    459
    +0.13
    0.7%
    497
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.15
    0.06
    300
    +0.13
    0.03
    404
    +0.13
    0.05
    Negative Logits
    dp
    -1.89
    vc
    -1.45
    dg
    -1.45
    ede
    -1.41
     vec
    -1.41
     https
    -1.39
    hor
    -1.38
     std
    -1.38
     puff
    -1.34
     i
    -1.33
    POSITIVE LOGITS
     peroxidase
    1.58
     increased
    1.46
    smen
    1.42
    gets
    1.40
    casters
    1.39
     analogs
    1.37
     instruments
    1.36
    ãĤīãĤĮ
    1.34
    orption
    1.34
     aims
    1.34
    Activations Density 0.650%

    No Known Activations