© 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. 27929
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or organizations

    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
    +0.21
    1.3%
    376
    +0.16
    1.0%
    275
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.21
    0.01
    315
    +0.16
    0.01
    365
    +0.12
    0.01
    Negative Logits
    ³
    -2.24
    ı
    -2.18
    §
    -2.18
    µ
    -2.09
    ĵ
    -2.06
    Ĵ
    -1.91
    Ń
    -1.88
    Ĺ
    -1.88
    ±
    -1.87
    ¥
    -1.87
    POSITIVE LOGITS
    pile
    1.82
    ULAR
    1.78
    pot
    1.75
    cript
    1.72
    etting
    1.72
    erve
    1.69
    manship
    1.68
    ystems
    1.67
    hell
    1.63
    iliary
    1.57
    Activations Density 0.065%

    No Known Activations