© 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. 27188
    Prev
    Next
    INDEX
    Explanations

    references to various medical syndromes 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
    271
    +0.12
    0.7%
    261
    +0.11
    0.6%
    500
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.00
    361
    +0.11
    0.01
    26
    +0.11
    0.01
    Negative Logits
     fois
    -1.85
    ibles
    -1.71
     vain
    -1.62
     hope
    -1.60
     yours
    -1.59
     meu
    -1.55
     serv
    -1.54
    oxacin
    -1.50
     HREF
    -1.48
     sweat
    -1.47
    POSITIVE LOGITS
    arial
    1.97
    emia
    1.94
     affecting
    1.77
    atics
    1.75
    case
    1.69
     involving
    1.60
    plasty
    1.59
    emic
    1.57
    atin
    1.55
     occurring
    1.53
    Activations Density 0.046%

    No Known Activations