© 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 EvalsExportsAPI 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. 27455
    Prev
    Next
    INDEX
    Explanations

    terminology related to healthcare and medical procedures

    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
    200
    +0.13
    0.7%
    23
    +0.12
    0.7%
    182
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.13
    0.03
    503
    +0.12
    0.02
    334
    +0.12
    0.02
    Negative Logits
    grounds
    -1.70
    ulates
    -1.59
     respects
    -1.52
     defects
    -1.52
     shown
    -1.49
     magnification
    -1.49
     sense
    -1.46
     thereon
    -1.44
     magn
    -1.42
     therein
    -1.41
    POSITIVE LOGITS
    º
    3.83
    ©
    3.64
    ¯
    3.59
    ł
    3.40
    «
    3.32
    ¨
    3.30
    ±
    3.19
    £
    3.17
    ¤
    3.08
    ¡
    3.06
    Activations Density 0.270%

    No Known Activations