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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30298
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific legal or licensing terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    47
    +0.13
    0.8%
    450
    +0.12
    0.7%
    186
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    89
    +0.13
    0.03
    341
    +0.12
    0.03
    329
    +0.12
    0.02
    Negative Logits
    »¿
    -2.78
    ľĵ
    -2.72
    ®
    -2.51
    ↵
    -2.47
    ↵
    -2.47
    -2.47
    <|outofrange|>
    -2.47
    -2.47
              ↵
    -2.47
    -2.47
    POSITIVE LOGITS
    iator
    1.70
    елÑĮ
    1.37
    ÑĮ
    1.36
    å¯
    1.34
    ãĥ¼ãĤ¸
    1.30
    à¨
    1.29
    oslov
    1.29
     indemn
    1.26
    ified
    1.25
     Ernst
    1.23
    Activations Density 0.142%

    No Known Activations