© 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. 26822
    Prev
    Next
    INDEX
    Explanations

    the word "With" at the beginning of sentences

    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
    +0.23
    1.3%
    478
    +0.19
    1.1%
    115
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    358
    +0.23
    0.04
    447
    +0.19
    0.04
    35
    +0.14
    0.03
    Negative Logits
    igraph
    -1.54
    inos
    -1.52
    LECT
    -1.51
    ---|---
    -1.49
    ately
    -1.47
    ======
    -1.43
    ÅĽci
    -1.42
    ter
    -1.39
    fully
    -1.38
    wic
    -1.36
    POSITIVE LOGITS
     respect
    2.58
     regard
    2.40
     regards
    2.13
    drawn
    1.64
     certainty
    1.63
    ils
    1.56
    draw
    1.53
    growth
    1.53
    eland
    1.51
     luck
    1.51
    Activations Density 0.635%

    No Known Activations