© 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. 4-RES-SM
    11. 9073
    Prev
    Next
    INDEX
    Explanations

    references to JavaScript and jQuery

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    274
    +0.15
    0.9%
    281
    +0.13
    0.8%
    156
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.15
    0.03
    118
    +0.13
    0.02
    189
    +0.13
    0.02
    Negative Logits
    degree
    -1.94
    ascus
    -1.68
    waters
    -1.61
    lessness
    -1.60
    ignon
    -1.55
    ards
    -1.52
    liness
    -1.52
    ilateral
    -1.51
     contrary
    -1.51
    coli
    -1.49
    POSITIVE LOGITS
     ajax
    2.21
     Ajax
    2.19
    JS
    2.04
     DOM
    1.98
    fiddle
    1.97
    js
    1.97
     plugin
    1.95
     plugins
    1.90
     Plugin
    1.89
     UI
    1.89
    Activations Density 0.174%

    No Known Activations