© 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. 4-RES-SM
    11. 10259
    Prev
    Next
    INDEX
    Explanations

    terms related to health and medical conditions, especially those concerning infections or viruses

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.23
    1.4%
    203
    +0.11
    0.7%
    479
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.23
    0.02
    148
    +0.11
    0.02
    202
    +0.10
    0.00
    Negative Logits
     handy
    -1.47
     qual
    -1.39
    gage
    -1.33
     fact
    -1.32
    cent
    -1.31
     mind
    -1.30
     Lights
    -1.30
     belt
    -1.27
    jection
    -1.26
     jack
    -1.25
    POSITIVE LOGITS
    ĨĴ
    2.52
    ģ
    2.47
    Ĭ
    2.40
    ³
    2.28
    ĻĤ
    2.23
    Ī
    2.19
    Ļ
    2.14
    Į
    2.10
    į
    2.07
    IJ
    2.07
    Activations Density 0.110%

    No Known Activations