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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23761
    Prev
    Next
    INDEX
    Explanations

    references to legal opinions and court-related terms

    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
    +0.13
    0.7%
    488
    +0.13
    0.7%
    469
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.13
    0.06
    416
    +0.13
    0.05
    419
    +0.10
    0.02
    Negative Logits
     '"
    -1.56
     ">
    -1.42
     dispositions
    -1.38
    —"
    -1.38
    —'
    -1.34
    '"
    -1.33
     regulation
    -1.33
     EMS
    -1.31
     ([**
    -1.31
    '">
    -1.31
    POSITIVE LOGITS
    Ł
    2.10
    res
    1.80
    ı
    1.74
    Ĵ
    1.74
    Ñīе
    1.72
    abb
    1.64
    Ñĥм
    1.51
    ests
    1.50
    Ñĥд
    1.46
    »
    1.46
    Activations Density 1.480%

    No Known Activations