© 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. 29284
    Prev
    Next
    INDEX
    Explanations

    instances of official documents or orders being issued

    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
    376
    +0.14
    0.8%
    493
    +0.13
    0.7%
    467
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    493
    +0.14
    0.02
    351
    +0.13
    0.02
    467
    +0.12
    0.02
    Negative Logits
    olia
    -1.78
    ikel
    -1.65
     Island
    -1.63
     Islands
    -1.54
    auc
    -1.45
    ores
    -1.44
    enia
    -1.43
     island
    -1.42
    ang
    -1.39
     Builder
    -1.38
    POSITIVE LOGITS
     officials
    1.52
    gated
    1.44
     mailing
    1.40
     forth
    1.36
     pronounce
    1.36
    ICE
    1.35
    inals
    1.35
     lately
    1.35
    vendor
    1.35
     notice
    1.35
    Activations Density 0.141%

    No Known Activations