© 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. 2-MLP-SM
    11. 25536
    Prev
    Next
    INDEX
    Explanations

    phrases related to software licenses and legal disclaimers

    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
    414
    +0.12
    0.7%
    87
    +0.12
    0.7%
    480
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    207
    +0.12
    0.05
    504
    +0.12
    0.02
    77
    +0.10
    0.03
    Negative Logits
    isma
    -1.73
    otics
    -1.67
    inate
    -1.58
    hib
    -1.56
     vacancy
    -1.50
    ache
    -1.48
    oscal
    -1.48
    )$)
    -1.43
    ribe
    -1.42
    )',
    -1.39
    POSITIVE LOGITS
    Ŀ
    2.34
    ¾
    2.04
    ļ
    1.97
    ¦
    1.89
    ½
    1.88
    İ
    1.82
    ħ
    1.79
    ª
    1.73
    ¼
    1.72
    ľ
    1.70
    Activations Density 1.395%

    No Known Activations