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. 27570
    Prev
    Next
    INDEX
    Explanations

    references to glucose-related terms or concepts

    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
    369
    +0.17
    1.0%
    148
    +0.14
    0.8%
    354
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.17
    0.02
    259
    +0.14
    0.02
    359
    +0.12
    0.02
    Negative Logits
    ¥
    -2.52
    Ĥ
    -2.29
    ĥ
    -2.24
    ĩ
    -2.24
    Ĭ
    -2.21
    ħ
    -2.15
    Ĺ
    -2.14
    Ļª
    -2.08
    ria
    -2.07
    ¼
    -2.03
    POSITIVE LOGITS
          
    1.59
    GET
    1.54
    eval
    1.51
    stones
    1.51
     conceded
    1.50
    holders
    1.48
    gate
    1.46
     owned
    1.41
     supported
    1.37
    DAC
    1.37
    Activations Density 0.018%

    No Known Activations