© 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. 27651
    Prev
    Next
    INDEX
    Explanations

    terms related to physical health and medical professions

    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
    510
    +0.14
    0.8%
    356
    +0.14
    0.8%
    350
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.14
    0.01
    350
    +0.14
    0.03
    391
    +0.13
    0.02
    Negative Logits
    ESULT
    -1.58
     warrant
    -1.58
    lando
    -1.52
    xit
    -1.52
    roup
    -1.51
    InstanceState
    -1.50
    akes
    -1.48
    ľĵ
    -1.46
     continents
    -1.42
    npmjs
    -1.42
    POSITIVE LOGITS
    ician
    2.22
    icians
    2.21
    ically
    2.05
    ics
    1.74
    arum
    1.71
    ico
    1.68
    aret
    1.59
    urally
    1.57
    iedad
    1.56
    ural
    1.56
    Activations Density 0.181%

    No Known Activations