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. 27235
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Forum"

    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
    +0.25
    1.6%
    376
    +0.14
    0.9%
    181
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.25
    0.01
    126
    +0.14
    0.01
    14
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.02
     lovely
    -1.70
      ↵
    -1.67
    omers
    -1.63
     wonderful
    -1.54
    woke
    -1.53
     nice
    -1.52
     former
    -1.51
     elderly
    -1.50
     somebody
    -1.49
    POSITIVE LOGITS
    stab
    1.88
    ,[
    1.77
    yard
    1.72
    lane
    1.63
    ucc
    1.62
    isión
    1.55
    ÃŃo
    1.54
    liga
    1.52
    pole
    1.52
    ual
    1.52
    Activations Density 0.009%

    No Known Activations