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. 27349
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "minutes."

    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
    162
    +0.11
    0.6%
    457
    +0.11
    0.6%
    94
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.11
    0.03
    162
    +0.11
    0.03
    284
    +0.10
    0.03
    Negative Logits
     authors
    -1.61
     Month
    -1.53
     sorts
    -1.48
    acial
    -1.45
    t
    -1.44
     least
    -1.43
     yours
    -1.41
     Species
    -1.40
    rian
    -1.39
    CDATA
    -1.37
    POSITIVE LOGITS
    ¢
    2.04
    ®
    1.96
    ¥
    1.87
    µ
    1.72
    ª
    1.71
    ĩ
    1.70
    strom
    1.67
    «
    1.62
    ume
    1.57
    pieces
    1.57
    Activations Density 0.021%

    No Known Activations