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. 27362
    Prev
    Next
    INDEX
    Explanations

    phrases conveying strong emotional sentiments

    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
    381
    +0.11
    0.6%
    479
    +0.11
    0.6%
    78
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.11
    0.07
    170
    +0.11
    0.06
    421
    +0.11
    0.05
    Negative Logits
    Tex
    -1.64
    ôle
    -1.61
    ↵³³
    -1.54
    ération
    -1.50
     Vermont
    -1.42
    ître
    -1.41
    Å¡
    -1.40
    ô
    -1.37
    asting
    -1.36
     Sgt
    -1.36
    POSITIVE LOGITS
    paces
    1.49
    ARY
    1.45
    ystem
    1.43
    lining
    1.43
    arial
    1.41
     contrary
    1.39
    iae
    1.39
    erated
    1.38
    eri
    1.35
     Nations
    1.33
    Activations Density 0.107%

    No Known Activations