© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28003
    Prev
    Next
    INDEX
    Explanations

    repetitive use of the word "you."

    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
    198
    +0.14
    0.8%
    344
    +0.11
    0.6%
    202
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.14
    0.18
    473
    +0.11
    0.18
    266
    +0.10
    0.16
    Negative Logits
    °
    -1.96
    ī
    -1.52
    ĥ
    -1.52
    ®
    -1.52
     developer
    -1.44
    Ī
    -1.42
    ³
    -1.41
    že
    -1.38
     mate
    -1.38
    ĸ´
    -1.34
    POSITIVE LOGITS
    itudes
    1.72
    itation
    1.66
    itud
    1.54
     magazines
    1.54
    opic
    1.50
    chin
    1.47
    aday
    1.45
    itations
    1.41
    ÃŃo
    1.40
     accompany
    1.37
    Activations Density 0.396%

    No Known Activations