© 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. 23461
    Prev
    Next
    INDEX
    Explanations

    instances of appreciation or gratitude

    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
    31
    +0.13
    0.7%
    499
    +0.12
    0.6%
    135
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.13
    0.02
    499
    +0.12
    0.06
    405
    +0.11
    0.06
    Negative Logits
    steine
    -1.57
    ITY
    -1.56
    heit
    -1.55
    ^](#
    -1.51
    TRODUCTION
    -1.51
     BGCOLOR
    -1.48
     feeling
    -1.42
    ité
    -1.42
     stuff
    -1.37
    ients
    -1.36
    POSITIVE LOGITS
    ney
    1.59
    ophone
    1.44
     PubMed
    1.44
     session
    1.44
    uitable
    1.42
    née
    1.34
     simulator
    1.34
    table
    1.34
     instance
    1.33
    Īĺ
    1.32
    Activations Density 0.660%

    No Known Activations