© 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. 1-RES-SM
    11. 28749
    Prev
    Next
    INDEX
    Explanations

    references to "Chromebook" and variations of the word "chromium"

    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
    431
    +0.13
    0.7%
    500
    +0.13
    0.7%
    203
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.03
    271
    +0.13
    0.00
    156
    +0.13
    0.02
    Negative Logits
     welcome
    -1.88
    ftware
    -1.87
     course
    -1.58
     massive
    -1.58
    ccess
    -1.57
     late
    -1.57
     prospective
    -1.55
    coming
    -1.54
    illance
    -1.50
     behalf
    -1.49
    POSITIVE LOGITS
    owitz
    1.91
    ophore
    1.87
    stones
    1.75
    antine
    1.69
    ophores
    1.64
    ium
    1.61
     Films
    1.60
    aine
    1.59
    ospheric
    1.57
    inski
    1.56
    Activations Density 0.148%

    No Known Activations