© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28787
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare policies and practices

    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
    186
    +0.24
    1.4%
    156
    +0.20
    1.2%
    47
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.24
    0.13
    490
    +0.20
    0.10
    186
    +0.14
    0.08
    Negative Logits
    ème
    -1.78
    documentclass
    -1.60
    umab
    -1.59
     pudding
    -1.51
    etus
    -1.50
     cake
    -1.48
     Boltzmann
    -1.41
     illustr
    -1.40
     necklace
    -1.38
     button
    -1.38
    POSITIVE LOGITS
    Ļª
    2.06
    ĥ
    1.88
    Ł
    1.63
    Īĺ
    1.61
    ¼
    1.60
    mun
    1.53
    arma
    1.49
     particular
    1.48
    ull
    1.47
    Ĥ¬
    1.45
    Activations Density 1.784%

    No Known Activations