© 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. 26991
    Prev
    Next
    INDEX
    Explanations

    terms related to chronic illnesses and conditions

    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
    +0.24
    1.3%
    186
    +0.13
    0.7%
    253
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.24
    0.01
    253
    +0.13
    0.01
    448
    +0.11
    0.01
    Negative Logits
    že
    -1.86
     suitable
    -1.66
    ÈĻ
    -1.65
     convenient
    -1.53
    owed
    -1.50
     portable
    -1.49
    ÅŁ
    -1.49
     particular
    -1.45
     destination
    -1.45
    illed
    -1.40
    POSITIVE LOGITS
    Ł
    3.15
    £
    2.98
    ¾
    2.94
    ł
    2.85
    ¼
    2.81
    º
    2.74
    ·
    2.70
    ļ
    2.69
    Ĩ
    2.66
    ¹
    2.52
    Activations Density 0.033%

    No Known Activations