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. 27610
    Prev
    Next
    INDEX
    Explanations

    occurrences of articles and prepositions

    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
    233
    +0.11
    0.6%
    410
    +0.10
    0.6%
    82
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.11
    0.16
    321
    +0.10
    0.17
    440
    +0.09
    0.18
    Negative Logits
    tons
    -1.68
    chen
    -1.54
     synthes
    -1.44
    forward
    -1.41
     analytical
    -1.40
     exped
    -1.40
     sequentially
    -1.38
     frequency
    -1.38
     fast
    -1.37
     elliptic
    -1.33
    POSITIVE LOGITS
    ¦
    2.79
    Ń
    2.65
    ±
    2.44
    Ĥ¬
    2.34
    »¿
    2.34
    ¾
    2.32
    ¢
    2.32
    ¿½
    2.25
    ¡
    2.25
    Ļ
    2.23
    Activations Density 1.722%

    No Known Activations