© 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. 25494
    Prev
    Next
    INDEX
    Explanations

    legal terms related to appellants and appellees in 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
    260
    +0.12
    0.7%
    360
    +0.12
    0.7%
    283
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    94
    +0.12
    0.02
    260
    +0.12
    0.01
    462
    +0.11
    0.01
    Negative Logits
     occasions
    -1.65
    ©
    -1.49
    CDATA
    -1.32
    ently
    -1.32
     longer
    -1.30
     PBX
    -1.29
    ĵ
    -1.29
    erad
    -1.28
    ICAN
    -1.27
    ographically
    -1.27
    POSITIVE LOGITS
     ourselves
    1.67
    ayers
    1.66
    han
    1.61
    :`
    1.54
    ayer
    1.53
    ères
    1.51
    ulus
    1.51
    das
    1.49
    sense
    1.48
    fficients
    1.40
    Activations Density 0.031%

    No Known Activations