© 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. 25212
    Prev
    Next
    INDEX
    Explanations

    keywords related to neurodegenerative diseases, particularly ALS and dementia

    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%
    206
    +0.12
    0.7%
    241
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.04
    321
    +0.12
    0.03
    241
    +0.12
    0.03
    Negative Logits
    ¿½
    -3.15
    ¼
    -2.33
    Ŀ
    -2.23
    ±
    -2.15
    ¬
    -2.15
    ĺ
    -2.14
    IJ
    -2.14
    ¾
    -2.12
    ¯
    -2.12
    ´
    -2.08
    POSITIVE LOGITS
     cases
    1.96
     case
    1.79
     risk
    1.79
    scape
    1.73
     mellitus
    1.67
     burden
    1.65
     adversely
    1.63
     diagnosis
    1.63
    sson
    1.63
    case
    1.61
    Activations Density 0.123%

    No Known Activations