© 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. 28111
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmaceutical and drug development processes

    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
    61
    +0.13
    0.7%
    420
    +0.13
    0.7%
    116
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.13
    0.02
    116
    +0.13
    0.01
    59
    +0.13
    0.01
    Negative Logits
     homeland
    -1.62
     welcome
    -1.62
     whereabouts
    -1.55
    Bye
    -1.55
     battlefield
    -1.49
     living
    -1.49
    OTHER
    -1.48
    cause
    -1.45
     suspect
    -1.42
     hometown
    -1.41
    POSITIVE LOGITS
    inx
    1.93
    ¥
    1.82
    ambda
    1.79
    ley
    1.78
    leys
    1.76
    ancer
    1.76
    ifer
    1.72
    ateral
    1.72
    uted
    1.67
    Ł
    1.66
    Activations Density 0.117%

    No Known Activations