© 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. 4-RES-SM
    11. 12702
    Prev
    Next
    INDEX
    Explanations

    instances of code or programming syntax

    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
    78
    +0.17
    1.0%
    478
    +0.12
    0.7%
    126
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    191
    +0.17
    0.05
    454
    +0.12
    0.03
    9
    +0.12
    0.04
    Negative Logits
    umab
    -1.64
     liability
    -1.58
     wheelchair
    -1.45
    sson
    -1.44
    burgh
    -1.37
    lying
    -1.32
    eron
    -1.31
    bell
    -1.29
    omers
    -1.29
    erate
    -1.24
    POSITIVE LOGITS
    ĭ
    3.34
    ¤
    3.01
    İ
    3.00
    «
    2.98
    Ŀ
    2.95
    ¦
    2.89
    ³
    2.89
    IJ
    2.87
    º
    2.85
    ¥
    2.82
    Activations Density 0.232%

    No Known Activations