© 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 EvalsExportsAPI 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. 27814
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and references associated with patents or technical 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
    507
    +0.15
    0.8%
    104
    +0.12
    0.7%
    398
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.15
    0.03
    408
    +0.12
    0.02
    425
    +0.12
    0.02
    Negative Logits
     ðŁ
    -1.85
    *.
    -1.51
     checkpoint
    -1.50
     round
    -1.49
     victim
    -1.48
     ðŁĺ
    -1.44
     Halloween
    -1.43
     boo
    -1.42
    ?!
    -1.42
    !}
    -1.42
    POSITIVE LOGITS
     embodiments
    1.81
     patent
    1.80
     Patent
    1.77
     hereinafter
    1.70
     patents
    1.67
    papers
    1.64
    Patent
    1.59
     inventions
    1.58
     estoppel
    1.55
     herein
    1.51
    Activations Density 0.235%

    No Known Activations