© 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. 10174
    Prev
    Next
    INDEX
    Explanations

    terms related to various forms of medicine and complementary therapies

    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
    427
    +0.18
    1.0%
    287
    +0.13
    0.7%
    34
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    427
    +0.18
    0.08
    187
    +0.13
    0.06
    34
    +0.12
    0.16
    Negative Logits
    ;</
    -1.76
    >{
    -1.68
     <
    -1.63
    </
    -1.61
    .</
    -1.58
    >:
    -1.53
    !”
    -1.51
    .—
    -1.50
    ">
    -1.48
    ;">
    -1.47
    POSITIVE LOGITS
     surely
    1.54
    aring
    1.36
     mergers
    1.33
     playoffs
    1.30
     "*
    1.28
     Dayton
    1.28
     NATO
    1.27
    played
    1.26
    thems
    1.25
     NASA
    1.22
    Activations Density 7.086%

    No Known Activations