© 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 EvalsExportsinterp-engineNEWAPI 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. 30614
    Prev
    Next
    INDEX
    Explanations

    references to encoding standards, specifically highlighting UTF-8

    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
    +0.17
    1.0%
    283
    +0.12
    0.7%
    430
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.17
    0.01
    430
    +0.12
    0.01
    90
    +0.11
    0.01
    Negative Logits
    ı
    -3.26
    Ĥ
    -3.25
    IJ
    -3.21
    µ
    -3.19
    ³
    -3.03
    Ĥ¬
    -2.90
    »
    -2.88
    Ĺ
    -2.84
    ·
    -2.81
    ¹
    -2.81
    POSITIVE LOGITS
     styles
    1.88
     format
    1.77
     modality
    1.67
    idone
    1.67
     formats
    1.64
     style
    1.57
     languages
    1.56
    batim
    1.55
     genres
    1.48
    fonts
    1.48
    Activations Density 0.020%

    No Known Activations