© 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. 4-RES-SM
    11. 12181
    Prev
    Next
    INDEX
    Explanations

    terms related to specific diseases and their treatments

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    156
    +0.30
    1.9%
    307
    +0.20
    1.2%
    25
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.30
    0.05
    413
    +0.20
    0.04
    134
    +0.18
    0.08
    Negative Logits
     ÑĩÑĤо
    -1.61
     Customer
    -1.54
     WHERE
    -1.44
    č↵
    -1.43
     ÑįÑĤо
    -1.41
     booking
    -1.41
    >>>
    -1.41
     analytics
    -1.40
    }</
    -1.39
     Audio
    -1.36
    POSITIVE LOGITS
    ocytes
    2.35
    ocyte
    2.11
    idin
    1.97
    otoxin
    1.96
    rosis
    1.95
    idine
    1.95
    ocytic
    1.94
    ulin
    1.91
    rocytes
    1.88
    omonas
    1.83
    Activations Density 1.040%

    No Known Activations