© 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. 12536
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate responses or treatments in medical contexts

    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
    0.9%
    199
    +0.12
    0.7%
    5
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.15
    0.02
    433
    +0.12
    0.01
    5
    +0.11
    0.02
    Negative Logits
    ĥ½
    -2.30
    roe
    -2.22
    ¿½
    -2.08
    llll
    -1.71
    kered
    -1.71
    izi
    -1.70
    xico
    -1.70
    oxacin
    -1.68
     Appeal
    -1.68
    »¿
    -1.66
    POSITIVE LOGITS
     triggered
    1.64
     alert
    1.63
     element
    1.57
     response
    1.55
     rate
    1.53
     rates
    1.51
     callback
    1.51
     elicited
    1.48
     weak
    1.47
     emitted
    1.46
    Activations Density 0.097%

    No Known Activations