© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-SM
    11. 12012
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and binding structures

    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
    235
    +0.14
    0.8%
    484
    +0.13
    0.8%
    338
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.14
    0.03
    172
    +0.13
    0.04
    484
    +0.13
    0.01
    Negative Logits
    ½
    -2.13
    Ħ
    -1.96
     Mega
    -1.95
    ¾
    -1.75
    Ĥ
    -1.71
    ¿½
    -1.67
     fry
    -1.66
    ı
    -1.65
    ´
    -1.64
    İ
    -1.62
    POSITIVE LOGITS
     binding
    3.86
     Binding
    3.66
     bind
    3.33
    binding
    3.31
     bindings
    3.27
    Binding
    3.18
     binds
    3.02
     ligand
    3.01
     ligands
    2.90
     bound
    2.88
    Activations Density 0.642%

    No Known Activations