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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28602
    Prev
    Next
    INDEX
    Explanations

    references to the Python programming language and related libraries

    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
    156
    +0.29
    1.7%
    410
    +0.13
    0.7%
    321
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.29
    0.01
    431
    +0.13
    0.01
    298
    +0.13
    0.02
    Negative Logits
    ĥ½
    -1.80
    ·
    -1.77
    ľĵ
    -1.72
    uality
    -1.69
    Ĭ
    -1.56
    ľ
    -1.54
    ı
    -1.52
    ĭ
    -1.50
    ori
    -1.49
    ĺ
    -1.47
    POSITIVE LOGITS
    bing
    1.81
    erals
    1.61
     interpreter
    1.60
     tutorials
    1.51
     versions
    1.48
    80211
    1.47
    Script
    1.45
     tutorial
    1.45
    cias
    1.44
     version
    1.43
    Activations Density 0.077%

    No Known Activations