© 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. 27927
    Prev
    Next
    INDEX
    Explanations

    mentions of enterprise-related concepts and terminology

    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
    43
    +0.11
    0.6%
    130
    +0.10
    0.6%
    186
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.11
    0.03
    418
    +0.10
    -0.01
    365
    +0.10
    0.03
    Negative Logits
     louder
    -1.63
     excess
    -1.59
     excessive
    -1.56
    uke
    -1.52
     audible
    -1.51
     foul
    -1.48
    arest
    -1.47
     slight
    -1.46
     tears
    -1.45
     guilty
    -1.44
    POSITIVE LOGITS
    "}](#
    2.08
    prises
    1.97
    prise
    1.75
    FC
    1.59
    vironment
    1.58
    belt
    1.57
    NER
    1.56
     projects
    1.55
    folio
    1.50
     Organisation
    1.49
    Activations Density 0.525%

    No Known Activations