© 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. 26840
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions associated with health risks and safety

    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
    +0.27
    1.6%
    56
    +0.22
    1.3%
    18
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.27
    -0.05
    238
    +0.22
    0.12
    176
    +0.11
    0.16
    Negative Logits
     unified
    -1.74
     kb
    -1.74
    isenberg
    -1.67
     ÏĮÏĦι
    -1.60
    unity
    -1.60
     ferm
    -1.58
     topology
    -1.58
     hospitality
    -1.54
     conceptual
    -1.54
     championship
    -1.52
    POSITIVE LOGITS
    .\[[@
    1.71
    chant
    1.70
     depending
    1.67
    requently
    1.62
     injured
    1.57
     lasting
    1.56
    plasty
    1.56
     healthy
    1.56
     follicles
    1.54
     disease
    1.52
    Activations Density 5.670%

    No Known Activations