© 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. 0-MLP-SM
    11. 27816
    Prev
    Next
    INDEX
    Explanations

    legal concepts related to court rulings and trial outcomes

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.15
    0.8%
    376
    +0.13
    0.7%
    143
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.15
    0.01
    235
    +0.13
    0.01
    480
    +0.12
    0.01
    Negative Logits
    ±
    -3.61
    Ĵ
    -3.58
    ¸
    -3.55
    ¯
    -3.44
    ĥ½
    -3.40
    ½
    -3.38
    Ł
    -3.37
    ¼
    -3.34
    ´
    -3.22
    ĵ
    -3.18
    POSITIVE LOGITS
    pora
    1.70
    ulum
    1.61
    cript
    1.56
    nell
    1.51
    rypt
    1.46
     houses
    1.46
    iella
    1.45
     chambers
    1.44
     succession
    1.43
    rior
    1.43
    Activations Density 0.099%

    No Known Activations