© 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. 27648
    Prev
    Next
    INDEX
    Explanations

    references to ultrasound and related imaging techniques

    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
    +0.25
    1.4%
    114
    +0.12
    0.7%
    438
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.25
    0.00
    114
    +0.12
    0.01
    494
    +0.12
    0.01
    Negative Logits
    mates
    -1.85
     compromise
    -1.82
    mate
    -1.66
     unanimous
    -1.65
     everything
    -1.65
     unexpected
    -1.62
     bargaining
    -1.61
     outright
    -1.60
     surrender
    -1.57
     contradiction
    -1.56
    POSITIVE LOGITS
    ¢
    3.25
    µ
    2.95
    Ĵ
    2.95
    ·¸
    2.93
    ĭ
    2.85
    »¿
    2.80
    Ī
    2.77
    ¤
    2.77
    ħ
    2.76
    Ħ
    2.74
    Activations Density 0.076%

    No Known Activations