© 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. 2-RES-SM
    11. 12268
    Prev
    Next
    INDEX
    Explanations

    patterns related to software licensing and exceptions in code

    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
    29
    +0.14
    0.8%
    463
    +0.11
    0.6%
    121
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.14
    0.02
    456
    +0.11
    0.02
    218
    +0.11
    0.02
    Negative Logits
    olar
    -1.50
    posable
    -1.49
     Times
    -1.45
     territory
    -1.43
    occ
    -1.43
    adian
    -1.41
    indexOf
    -1.38
     inversion
    -1.36
    Pal
    -1.36
    lying
    -1.36
    POSITIVE LOGITS
    Īĺ
    2.39
    ĻĤ
    2.39
    ¼
    2.39
    Ħ
    2.19
    Ģ
    2.17
    ±
    2.16
    į
    2.14
    ¬
    2.08
    ģ
    2.06
    «
    2.05
    Activations Density 0.144%

    No Known Activations