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. 27285
    Prev
    Next
    INDEX
    Explanations

    instances of the word "presents."

    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
    376
    +0.22
    1.2%
    148
    +0.15
    0.8%
    115
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.22
    0.01
    372
    +0.15
    0.01
    74
    +0.14
    0.01
    Negative Logits
     <%=
    -1.53
     JavaScript
    -1.49
    ived
    -1.49
    liche
    -1.46
    s
    -1.44
    ober
    -1.43
    wik
    -1.41
     reputation
    -1.40
    romes
    -1.39
    ↵³³
    -1.37
    POSITIVE LOGITS
    cents
    1.76
    chool
    1.75
    ystems
    1.69
    omal
    1.69
    cent
    1.64
    omerase
    1.59
    ystem
    1.58
     ground
    1.50
    ational
    1.49
    addle
    1.46
    Activations Density 0.889%

    No Known Activations