© 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. 13239
    Prev
    Next
    INDEX
    Explanations

    terms related to electroconvulsive therapy (ECT) and medical conditions associated with it

    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
    143
    +0.12
    0.7%
    444
    +0.12
    0.7%
    248
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    399
    +0.12
    0.01
    444
    +0.12
    0.01
    315
    +0.11
    0.01
    Negative Logits
     such
    -1.69
    qa
    -1.63
     matter
    -1.57
    abol
    -1.52
    !}
    -1.47
    tering
    -1.47
    thems
    -1.46
     disposal
    -1.44
    dom
    -1.43
     convenient
    -1.40
    POSITIVE LOGITS
    ãĥ³ãĥĪ
    1.62
    ģ
    1.59
    ±
    1.57
     DISTRICT
    1.55
    ª
    1.54
    ENRON
    1.52
    °
    1.52
    DATE
    1.51
    IJ
    1.51
    «
    1.49
    Activations Density 0.097%

    No Known Activations