© 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. 1-RES-SM
    11. 28284
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatment or therapies

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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%
    376
    +0.15
    0.8%
    199
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.15
    0.02
    199
    +0.15
    0.01
    378
    +0.13
    0.02
    Negative Logits
    ŀ
    -3.05
    ĥ½
    -3.02
    Ń
    -2.99
    ĩ
    -2.83
    ĨĴ
    -2.75
    ¾
    -2.69
    Ŀ
    -2.63
    »
    -2.59
    Ī
    -2.58
    İ
    -2.56
    POSITIVE LOGITS
     surgically
    1.73
     identically
    1.71
    úblic
    1.57
    NU
    1.49
     conserv
    1.49
     Briefly
    1.47
     hour
    1.42
     overnight
    1.42
     with
    1.40
     himself
    1.39
    Activations Density 0.047%

    No Known Activations