© 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. 29393
    Prev
    Next
    INDEX
    Explanations

    repeated uses of the word "it."

    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
    444
    +0.13
    0.7%
    68
    +0.12
    0.7%
    37
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.22
    185
    +0.12
    0.18
    165
    +0.11
    0.17
    Negative Logits
    Ļª
    -1.81
    úblic
    -1.67
    ioned
    -1.64
    ĨĴ
    -1.58
    ®
    -1.53
    ¾
    -1.50
    ilent
    -1.48
    ↵            ↵
    -1.48
    ↵↵
    -1.48
    ↵
    -1.48
    POSITIVE LOGITS
    iments
    1.44
     solution
    1.40
    1371
    1.39
    1600
    1.39
     permutations
    1.29
     Kre
    1.28
    html
    1.26
    documentclass
    1.26
     alphabet
    1.26
     substitutions
    1.26
    Activations Density 0.398%

    No Known Activations