© 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 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. 25184
    Prev
    Next
    INDEX
    Explanations

    text related to legal cases and judicial rulings

    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
    156
    +0.29
    1.7%
    354
    +0.12
    0.7%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.29
    0.01
    23
    +0.12
    0.04
    360
    +0.12
    0.00
    Negative Logits
    ypse
    -1.90
    izumab
    -1.58
    iative
    -1.55
     Analytics
    -1.44
     BASIS
    -1.43
    ↵³³
    -1.38
    gorithm
    -1.37
     agent
    -1.36
    FPar
    -1.35
    pson
    -1.33
    POSITIVE LOGITS
     ye
    1.62
    ouring
    1.58
    oust
    1.56
     stir
    1.55
    asting
    1.46
    alling
    1.43
    oured
    1.43
    iNdEx
    1.42
    ours
    1.42
    oking
    1.38
    Activations Density 3.002%

    No Known Activations