© 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. 30456
    Prev
    Next
    INDEX
    Explanations

    phrases related to software licensing and usage permissions

    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
    +0.12
    0.7%
    17
    +0.12
    0.7%
    118
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.12
    0.04
    81
    +0.12
    0.03
    480
    +0.11
    0.03
    Negative Logits
    àµį
    -1.70
    ously
    -1.70
    ãĤĩ
    -1.58
    rus
    -1.50
    ving
    -1.49
    ful
    -1.48
    reatment
    -1.48
    ãĥ³
    -1.47
    ãĥĥãĥĪ
    -1.47
    imeter
    -1.43
    POSITIVE LOGITS
    Īĺ
    1.83
    ĥ½
    1.82
     possessions
    1.82
     suspects
    1.79
     winners
    1.69
     candidates
    1.69
     families
    1.68
     facts
    1.65
    ľĵ
    1.59
     ways
    1.56
    Activations Density 0.271%

    No Known Activations