© 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 EvalsExportsinterp-engineNEWAPI 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. 13925
    Prev
    Next
    INDEX
    Explanations

    specific types of touch technology and their classifications

    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
    156
    +0.30
    1.7%
    48
    +0.12
    0.7%
    104
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.30
    0.62
    156
    +0.12
    0.56
    71
    +0.12
    0.54
    Negative Logits
    ĥ½
    -1.73
     dataset
    -1.72
     outcome
    -1.51
    quartile
    -1.48
     questionnaire
    -1.47
    hab
    -1.46
     database
    -1.45
    ľĵ
    -1.43
     topic
    -1.43
     inbox
    -1.40
    POSITIVE LOGITS
     xe
    2.18
     embodiments
    1.84
     Examples
    1.77
     thereto
    1.71
    xe
    1.69
     manufacturers
    1.67
     _________________________________
    1.65
     patents
    1.60
    rely
    1.55
     discloses
    1.55
    Activations Density 2.271%

    No Known Activations