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. 27639
    Prev
    Next
    INDEX
    Explanations

    the definite article "the."

    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
    +0.13
    0.7%
    133
    +0.12
    0.6%
    346
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.13
    0.47
    98
    +0.12
    0.21
    228
    +0.11
    0.32
    Negative Logits
    "}](#
    -1.67
    ocations
    -1.58
    labelled
    -1.56
    arcin
    -1.56
    npmjs
    -1.49
    Errno
    -1.49
     reality
    -1.46
    undefined
    -1.44
    amaz
    -1.41
    aby
    -1.37
    POSITIVE LOGITS
    º
    2.85
    ģ
    2.67
    ĸ´
    2.62
    Īĺ
    2.56
    Ĥ¬
    2.55
    Ļª
    2.53
    »
    2.53
    ª
    2.49
    Ļ
    2.48
    ļ
    2.47
    Activations Density 2.922%

    No Known Activations