© 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. 28275
    Prev
    Next
    INDEX
    Explanations

    references to structured plans or systems, particularly in the context of health and fitness

    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
    +0.31
    2.0%
    376
    +0.15
    1.0%
    184
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.31
    0.01
    156
    +0.15
    0.01
    20
    +0.12
    0.01
    Negative Logits
    ĥ½
    -3.19
    Ĵ
    -2.56
    ¿½
    -2.49
    §
    -2.41
     ↵
    -2.36
    -2.36
    ↵
    -2.36
    ↵↵
    -2.36
    -2.36
    -2.36
    POSITIVE LOGITS
    "}](#
    1.58
    etable
    1.56
     appears
    1.55
    aments
    1.54
    cles
    1.48
     begins
    1.47
     consists
    1.44
    enoid
    1.44
    fork
    1.43
    doms
    1.42
    Activations Density 0.009%

    No Known Activations