© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27747
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions or treatments that involve inhibition or suppression

    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
    376
    +0.15
    0.8%
    320
    +0.13
    0.7%
    253
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.15
    0.01
    408
    +0.13
    0.01
    200
    +0.11
    0.00
    Negative Logits
    ĨĴ
    -2.56
    ı
    -2.43
    ĸ´
    -2.29
    Ķ
    -2.29
    ½
    -2.27
    ¿
    -2.18
    ¸
    -2.17
    ĵ
    -2.17
    Į
    -2.17
    ©
    -2.15
    POSITIVE LOGITS
    ulate
    1.86
    ulator
    1.77
    ulated
    1.76
    ulled
    1.67
    erals
    1.51
    ulation
    1.47
    ulators
    1.45
    ulating
    1.45
     element
    1.43
    "}](#
    1.42
    Activations Density 0.004%

    No Known Activations