© 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. 26589
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Van" and variations thereof

    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
    59
    +0.22
    1.2%
    410
    +0.15
    0.8%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.22
    0.03
    410
    +0.15
    0.03
    369
    +0.14
    0.01
    Negative Logits
     continuation
    -1.59
     chance
    -1.58
     fault
    -1.57
     television
    -1.54
    osing
    -1.51
     minor
    -1.51
     expected
    -1.50
     choice
    -1.47
     soccer
    -1.45
     football
    -1.45
    POSITIVE LOGITS
    ĻĤ
    2.40
    ¬
    2.28
    bilt
    1.85
    º
    1.78
    itas
    1.78
    ľĵ
    1.75
    Ĭ
    1.74
     himself
    1.73
    ī
    1.66
    imir
    1.64
    Activations Density 0.122%

    No Known Activations