© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27410
    Prev
    Next
    INDEX
    Explanations

    specific ratings or scores, particularly related to experiences or performances

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    369
    +0.20
    1.2%
    412
    +0.17
    1.0%
    95
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.20
    0.05
    95
    +0.17
    0.04
    377
    +0.15
    0.04
    Negative Logits
     kidding
    -1.75
    opus
    -1.62
    fer
    -1.55
    quo
    -1.52
    cludes
    -1.47
     answers
    -1.44
    terday
    -1.39
    swers
    -1.36
    igmat
    -1.34
    arus
    -1.33
    POSITIVE LOGITS
    erguson
    1.70
    ergus
    1.69
    olate
    1.59
    lickr
    1.57
    ayette
    1.55
    ountain
    1.54
    amilies
    1.53
    ECT
    1.52
    rees
    1.51
    inte
    1.49
    Activations Density 0.125%

    No Known Activations