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. 27447
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of admission, particularly in legal or formal 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
    156
    +0.12
    0.7%
    376
    +0.12
    0.7%
    115
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.12
    0.01
    312
    +0.12
    0.01
    347
    +0.11
    0.01
    Negative Logits
    vereign
    -1.84
    ollowing
    -1.72
    pher
    -1.61
    oxin
    -1.58
    harma
    -1.57
    izabeth
    -1.57
    akia
    -1.57
    aeda
    -1.54
    chard
    -1.53
    shore
    -1.53
    POSITIVE LOGITS
     trials
    1.89
    erior
    1.87
     variables
    1.83
     hearings
    1.71
     facie
    1.68
     tests
    1.63
    istical
    1.61
     matrices
    1.58
    figures
    1.55
     requirements
    1.55
    Activations Density 0.017%

    No Known Activations