© 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. 27218
    Prev
    Next
    INDEX
    Explanations

    references to the word "Smart"

    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
    156
    +0.25
    1.5%
    376
    +0.16
    1.0%
    148
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.25
    0.02
    79
    +0.16
    0.02
    173
    +0.14
    0.02
    Negative Logits
     darker
    -1.54
     warmer
    -1.53
     its
    -1.51
    versions
    -1.50
     abusive
    -1.46
     spite
    -1.38
     innocence
    -1.36
     inevitable
    -1.35
     '</
    -1.34
     poorer
    -1.33
    POSITIVE LOGITS
    ĻĤ
    2.34
    ģ
    2.23
    ĸ
    2.21
    Ł
    2.19
    stown
    2.08
    Ĵ
    2.06
    ķ
    2.03
    Ħ
    2.02
    ª
    1.85
    ±
    1.85
    Activations Density 0.015%

    No Known Activations