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. 27549
    Prev
    Next
    INDEX
    Explanations

    references to singleton instances in programming or data structures

    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
    1.5%
    376
    +0.17
    1.0%
    382
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.25
    0.39
    310
    +0.17
    0.31
    169
    +0.11
    0.28
    Negative Logits
    ub
    -1.40
    xy
    -1.36
    uke
    -1.35
    ____________
    -1.33
    ellow
    -1.31
     Eve
    -1.30
    uff
    -1.30
    avier
    -1.29
    orporated
    -1.29
    onas
    -1.29
    POSITIVE LOGITS
     types
    1.83
    hood
    1.80
    erals
    1.79
    pile
    1.68
     life
    1.63
    "}](#
    1.63
     ranges
    1.60
    plicity
    1.60
     mythology
    1.57
    stown
    1.54
    Activations Density 0.919%

    No Known Activations