© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26878
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to obligations or responsibilities

    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
    239
    +0.13
    0.7%
    301
    +0.11
    0.6%
    369
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.13
    0.04
    239
    +0.11
    0.12
    301
    +0.10
    0.06
    Negative Logits
    Ļª
    -1.96
    ģ
    -1.71
    ĻĤ
    -1.70
    orean
    -1.59
    ľĵ
    -1.58
    ilate
    -1.57
    ipl
    -1.57
     "</
    -1.50
     '</
    -1.49
    £
    -1.48
    POSITIVE LOGITS
     novels
    1.64
     textbooks
    1.60
     theories
    1.56
     protesters
    1.55
     paintings
    1.54
    nier
    1.48
     passengers
    1.43
     causes
    1.41
    cases
    1.41
     cups
    1.39
    Activations Density 2.556%

    No Known Activations