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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9707
    Prev
    Next
    INDEX
    Explanations

    terms related to stem cell research and related medical applications

    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
    235
    +0.15
    0.9%
    349
    +0.12
    0.7%
    278
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.15
    0.04
    235
    +0.12
    0.04
    73
    +0.12
    0.02
    Negative Logits
     slightest
    -1.88
     rude
    -1.69
     misunder
    -1.63
     misunderstanding
    -1.60
     noticed
    -1.57
     prejudiced
    -1.54
     laughed
    -1.54
    blogspot
    -1.52
     missed
    -1.49
    UTC
    -1.48
    POSITIVE LOGITS
    ants
    1.73
     consortium
    1.67
    rapeutics
    1.63
     transplantation
    1.60
     {#
    1.60
    )\]
    1.60
    aceuticals
    1.60
    aceutical
    1.58
    iator
    1.56
     adjuvant
    1.53
    Activations Density 0.529%

    No Known Activations