© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26519
    Prev
    Next
    INDEX
    Explanations

    data types and structures

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    416
    +0.15
    0.9%
    511
    +0.14
    0.8%
    23
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.15
    0.05
    511
    +0.14
    0.03
    416
    +0.13
    0.04
    Negative Logits
    £
    -2.28
    ĵ
    -2.17
    ©
    -2.12
    Ŀ
    -1.90
    Ĵ
    -1.84
    ¾
    -1.79
    »
    -1.75
    ¢
    -1.72
    Ľ
    -1.72
    ī
    -1.71
    POSITIVE LOGITS
    documentclass
    1.98
    )',
    1.91
    ,'"
    1.81
    yrs
    1.78
    fits
    1.72
    ('./
    1.64
    enties
    1.61
    hline
    1.54
     '')
    1.54
    compile
    1.52
    Activations Density 0.371%

    No Known Activations