Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27556
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "appellant" in legal contexts

    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
    333
    +0.13
    0.7%
    370
    +0.12
    0.7%
    295
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.13
    0.04
    370
    +0.12
    0.04
    331
    +0.10
    0.03
    Negative Logits
     BGCOLOR
    -1.78
    Argued
    -1.74
    dtd
    -1.64
     latter
    -1.57
    *](#
    -1.55
     /><
    -1.49
    Ļª
    -1.49
    itter
    -1.41
    >&
    -1.41
    ippy
    -1.39
    POSITIVE LOGITS
    pieces
    1.90
     deserves
    1.60
    phan
    1.60
    ée
    1.54
     camps
    1.52
    erals
    1.50
    ately
    1.50
    doms
    1.49
    bed
    1.49
     deserve
    1.48
    Activations Density 0.142%

    No Known Activations