© 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. 29680
    Prev
    Next
    INDEX
    Explanations

    terms related to patient care and healthcare services

    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
    394
    +0.17
    0.9%
    156
    +0.15
    0.9%
    486
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.17
    0.04
    486
    +0.15
    0.03
    418
    +0.12
    0.00
    Negative Logits
    µ
    -2.13
    ĻĤ
    -1.98
    ®
    -1.92
    ¿
    -1.90
    ĨĴ
    -1.86
    ·¸
    -1.83
    ³
    -1.82
    ı
    -1.82
    Ļª
    -1.80
    GREEK
    -1.79
    POSITIVE LOGITS
    ering
    1.91
    giving
    1.77
    zza
    1.71
    fully
    1.68
    ered
    1.56
    phal
    1.53
     center
    1.52
    era
    1.52
     available
    1.51
     needed
    1.50
    Activations Density 0.178%

    No Known Activations