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. 27614
    Prev
    Next
    INDEX
    Explanations

    instances of past tense verbs in the context of events or actions

    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
    56
    +0.13
    0.7%
    58
    +0.12
    0.7%
    421
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.35
    151
    +0.12
    0.26
    98
    +0.11
    0.11
    Negative Logits
     thereon
    -1.49
     primes
    -1.40
     showers
    -1.39
     weddings
    -1.39
     baths
    -1.39
    soever
    -1.37
     streams
    -1.35
     expects
    -1.33
     crowds
    -1.29
     teeth
    -1.28
    POSITIVE LOGITS
    uve
    1.45
    itage
    1.45
    documentclass
    1.43
    jour
    1.42
    aka
    1.41
    uk
    1.41
     nick
    1.39
    gard
    1.37
    leaf
    1.36
    jun
    1.36
    Activations Density 2.302%

    No Known Activations