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

    Neuronpedia

    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. 12186
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to health and wellness

    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
    250
    +0.12
    0.7%
    183
    +0.12
    0.7%
    503
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.12
    0.01
    503
    +0.12
    0.02
    386
    +0.12
    0.01
    Negative Logits
    nd
    -1.58
     peroxidase
    -1.58
    igner
    -1.54
    wise
    -1.53
    olated
    -1.45
    holds
    -1.43
     goodbye
    -1.41
    able
    -1.39
    arity
    -1.37
    avel
    -1.37
    POSITIVE LOGITS
    ³
    3.81
    ©
    3.75
    ¾
    3.58
    ¿
    3.47
    »
    3.43
    ²
    3.40
    º
    3.33
    ®
    3.28
    ĻĤ
    3.26
    ·
    3.21
    Activations Density 0.136%

    No Known Activations