© 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. 2-RES-SM
    11. 28039
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electromagnetism and electronic properties

    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
    47
    +0.16
    0.9%
    122
    +0.13
    0.8%
    86
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.16
    0.05
    354
    +0.13
    0.03
    8
    +0.13
    0.02
    Negative Logits
     edition
    -2.22
    ahoma
    -1.79
     editions
    -1.78
    thens
    -1.72
     vez
    -1.68
    eligible
    -1.66
     audiences
    -1.61
     vista
    -1.57
    onymous
    -1.57
     reput
    -1.56
    POSITIVE LOGITS
     emitted
    1.89
     flowing
    1.79
     electrons
    1.75
     coefficient
    1.73
     pulse
    1.69
     waveform
    1.68
     applied
    1.67
     pulses
    1.65
     transmitted
    1.64
     generator
    1.64
    Activations Density 0.393%

    No Known Activations