© 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. 13812
    Prev
    Next
    INDEX
    Explanations

    phrases indicating choices or options

    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
    478
    +0.12
    0.7%
    454
    +0.11
    0.7%
    126
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.12
    0.01
    454
    +0.11
    0.01
    391
    +0.11
    0.02
    Negative Logits
    Ļª
    -2.82
    -2.75
     ↵
    -2.75
    -2.75
    -2.75
    ↵
    -2.75
    ↵
    -2.75
    -2.75
    -2.75
       ↵
    -2.75
    POSITIVE LOGITS
     WARRANTY
    1.81
     permission
    1.65
     arbitrary
    1.62
     MERCHANTABILITY
    1.50
     -*-
    1.46
    ÑĤеÑĢ
    1.44
     else
    1.42
     GPL
    1.36
    LICENSE
    1.33
     NEGLIGENCE
    1.33
    Activations Density 0.043%

    No Known Activations