© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 29233
    Prev
    Next
    INDEX
    Explanations

    expressions of expectation or anticipation

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    376
    +0.18
    1.1%
    156
    +0.12
    0.7%
    18
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.18
    0.01
    18
    +0.12
    0.01
    149
    +0.11
    0.01
    Negative Logits
    vester
    -1.67
    erman
    -1.52
    TRODUCTION
    -1.50
    unnumbered
    -1.50
    anian
    -1.49
    OH
    -1.48
    aft
    -1.48
    ostat
    -1.47
    qa
    -1.47
     proposition
    -1.46
    POSITIVE LOGITS
     ones
    1.54
     starters
    1.52
     crunch
    1.51
     bubbles
    1.48
    heid
    1.48
     excited
    1.46
     viewing
    1.42
    burg
    1.42
     cancell
    1.41
    ality
    1.37
    Activations Density 0.014%

    No Known Activations