© 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. 2-RES-SM
    11. 30384
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or absence of certain conditions in patients

    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
    +0.23
    1.3%
    478
    +0.14
    0.8%
    283
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.23
    0.02
    283
    +0.14
    0.03
    440
    +0.13
    0.02
    Negative Logits
    imeter
    -1.75
    uler
    -1.61
    ursed
    -1.52
    atura
    -1.50
    ution
    -1.46
    _(
    -1.41
    imeters
    -1.39
    box
    -1.38
    thing
    -1.36
     footer
    -1.36
    POSITIVE LOGITS
    IJ
    2.41
     regard
    2.39
    Į
    2.37
    ĻĤ
    2.27
    ij
    2.23
    ľĵ
    2.10
     regards
    2.02
    »¿
    2.01
    ĸ
    2.00
    Ļª
    1.96
    Activations Density 0.118%

    No Known Activations