© 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. 29694
    Prev
    Next
    INDEX
    Explanations

    instances of references to visual elements or illustrations in documents

    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
    363
    +0.14
    0.8%
    139
    +0.10
    0.6%
    204
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.06
    139
    +0.10
    0.04
    363
    +0.10
    0.03
    Negative Logits
    Simplify
    -1.84
    []{
    -1.51
     policy
    -1.45
    uelle
    -1.44
     ministry
    -1.39
     IRA
    -1.37
    \.
    -1.35
     policies
    -1.33
     agents
    -1.33
    oire
    -1.33
    POSITIVE LOGITS
    naments
    1.70
    instein
    1.63
    ://
    1.61
    ky
    1.59
    ³
    1.55
     immers
    1.54
    appa
    1.49
     FIGS
    1.49
     sight
    1.48
     facie
    1.46
    Activations Density 0.494%

    No Known Activations