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. 27599
    Prev
    Next
    INDEX
    Explanations

    references to the Southern region or culture

    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
    362
    +0.19
    1.1%
    156
    +0.15
    0.9%
    339
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.19
    0.02
    362
    +0.15
    0.02
    192
    +0.13
    0.02
    Negative Logits
    yla
    -1.68
     second
    -1.66
     more
    -1.59
    rogens
    -1.57
     '</
    -1.55
    eter
    -1.54
    asing
    -1.53
    fts
    -1.52
    deal
    -1.49
     course
    -1.49
    POSITIVE LOGITS
    Īĺ
    1.85
    estone
    1.79
    estock
    1.77
    cript
    1.76
    matter
    1.72
    bourne
    1.69
    quart
    1.67
    Ł
    1.57
    ©
    1.57
    ibrary
    1.54
    Activations Density 0.014%

    No Known Activations