© 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. 4-RES-SM
    11. 10659
    Prev
    Next
    INDEX
    Explanations

    terms related to asthma and its symptoms

    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
    450
    +0.14
    0.8%
    21
    +0.13
    0.7%
    78
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.14
    0.02
    9
    +0.13
    0.01
    450
    +0.13
    0.01
    Negative Logits
     however
    -2.04
    ski
    -1.68
    ester
    -1.58
    however
    -1.50
    soever
    -1.48
    quel
    -1.33
     appointed
    -1.32
    dling
    -1.32
     else
    -1.30
    figure
    -1.30
    POSITIVE LOGITS
    rophys
    2.12
    rocyte
    2.11
    rophot
    2.09
    igmat
    2.08
    rocy
    2.07
    rology
    1.88
    rocytes
    1.83
    ounding
    1.83
    rod
    1.82
    oria
    1.77
    Activations Density 0.138%

    No Known Activations