© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11030
    Prev
    Next
    INDEX
    Explanations

    references to medical terminology or conditions

    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
    350
    +0.14
    0.8%
    348
    +0.13
    0.7%
    470
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.14
    0.04
    350
    +0.13
    0.04
    334
    +0.13
    0.03
    Negative Logits
     new
    -1.69
    IGHT
    -1.67
     future
    -1.57
    abouts
    -1.53
    izable
    -1.51
    INST
    -1.50
    bbe
    -1.41
    built
    -1.40
     full
    -1.40
     alive
    -1.39
    POSITIVE LOGITS
    irectional
    2.15
    ensch
    1.97
    irection
    1.91
    imension
    1.75
    neys
    1.73
    imensional
    1.72
    isciplinary
    1.70
    ollah
    1.70
    erm
    1.67
    erman
    1.66
    Activations Density 0.131%

    No Known Activations