© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27814
    Prev
    Next
    INDEX
    Explanations

    the word "holding."

    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
    +0.15
    0.8%
    274
    +0.13
    0.7%
    480
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.15
    0.02
    274
    +0.13
    0.02
    372
    +0.11
    0.02
    Negative Logits
    ¹
    -2.88
    ĵ
    -2.71
    ĨĴ
    -2.68
    IJ
    -2.53
    ©
    -2.52
    Ĵ
    -2.51
    ↵
    -2.51
     ↵
    -2.51
    -2.51
    č↵č↵
    -2.51
    POSITIVE LOGITS
    istics
    1.84
    ulated
    1.80
     capacity
    1.73
     exercises
    1.71
    emann
    1.66
     records
    1.59
    room
    1.58
     equations
    1.52
    enses
    1.52
     occasions
    1.52
    Activations Density 0.011%

    No Known Activations