© 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. 2-RES-SM
    11. 28846
    Prev
    Next
    INDEX
    Explanations

    references to inventions and legal terminology related to patents and disclosures

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    189
    +0.13
    0.7%
    365
    +0.12
    0.7%
    87
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.13
    0.01
    365
    +0.12
    0.01
    418
    +0.11
    0.00
    Negative Logits
    Īĺ
    -2.36
    Ĵ
    -2.09
    ¿
    -2.07
    ij
    -2.00
    ľĵ
    -1.96
    ĻĤ
    -1.91
    Ļª
    -1.88
    Ģ
    -1.75
    lot
    -1.74
    ĥ½
    -1.72
    POSITIVE LOGITS
     hast
    1.82
    ifically
    1.67
     itself
    1.63
     pertains
    1.44
    riz
    1.43
     insofar
    1.43
    isan
    1.39
     relates
    1.36
    artic
    1.34
     designers
    1.34
    Activations Density 0.038%

    No Known Activations