© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23259
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology and phrasing related to court cases

    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
    480
    +0.14
    0.8%
    342
    +0.13
    0.7%
    416
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    253
    +0.14
    0.04
    232
    +0.13
    0.09
    348
    +0.13
    -0.01
    Negative Logits
     hereinafter
    -1.72
     —
    -1.53
     (),
    -1.50
     whose
    -1.49
    -âĤ¬
    -1.48
     ÂŃ
    -1.47
     amid
    -1.47
     encl
    -1.47
     hence
    -1.46
     thus
    -1.46
    POSITIVE LOGITS
    ĻĤ
    2.80
    º
    2.31
    ĸ´
    2.24
     crap
    2.15
    ©
    2.09
    ±
    1.98
    Īĺ
    1.97
    ı
    1.90
    ²
    1.87
    ¹
    1.82
    Activations Density 2.297%

    No Known Activations