© 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 EvalsExportsinterp-engineNEWAPI 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. 31862
    Prev
    Next
    INDEX
    Explanations

    functional definitions and their return types in programming contexts

    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
    478
    +0.23
    1.3%
    142
    +0.15
    0.8%
    140
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    140
    +0.23
    0.01
    330
    +0.15
    0.01
    478
    +0.14
    0.00
    Negative Logits
    borough
    -1.82
    icum
    -1.78
    IPE
    -1.74
    ieri
    -1.73
    iture
    -1.70
    isp
    -1.69
    ¢
    -1.68
    ipes
    -1.62
    itures
    -1.60
    fall
    -1.59
    POSITIVE LOGITS
     none
    1.70
     ../../
    1.59
     tears
    1.56
     envy
    1.56
    -)
    1.51
     shelves
    1.49
    edly
    1.44
     favor
    1.40
     empathy
    1.33
     yes
    1.32
    Activations Density 0.096%

    No Known Activations