© 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 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. 9780
    Prev
    Next
    INDEX
    Explanations

    medical terms related to ischemia and occlusion

    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
    156
    +0.15
    0.8%
    47
    +0.13
    0.7%
    389
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    115
    +0.15
    0.01
    389
    +0.13
    0.02
    47
    +0.12
    0.02
    Negative Logits
    ably
    -1.87
     '</
    -1.77
    INGS
    -1.75
    >'
    -1.61
     guilty
    -1.59
    ="$(
    -1.51
    ="'
    -1.50
    unnumbered
    -1.48
     *.
    -1.47
     \\[
    -1.46
    POSITIVE LOGITS
     reperfusion
    1.87
     occurring
    1.77
    oxia
    1.71
     triggered
    1.66
    igon
    1.66
    etus
    1.63
     caused
    1.60
     induced
    1.58
    aused
    1.54
     conditioned
    1.53
    Activations Density 0.104%

    No Known Activations