© 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. 4-RES-SM
    11. 9560
    Prev
    Next
    INDEX
    Explanations

    references to multithreading and task management in programming

    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
    400
    +0.12
    0.6%
    307
    +0.11
    0.6%
    115
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.12
    0.04
    17
    +0.11
    0.02
    400
    +0.10
    0.01
    Negative Logits
    ł
    -2.72
    Ĩ
    -2.58
    §
    -2.36
    ĵ
    -2.23
    Ħ
    -2.23
    »¿
    -2.18
    IJ
    -2.16
    ¦
    -2.12
    ´
    -2.09
    ·
    -2.06
    POSITIVE LOGITS
    ing
    3.60
     sched
    2.13
    bare
    2.10
    pool
    2.06
    ingale
    1.96
    ed
    1.93
    mare
    1.92
    kill
    1.69
    ingen
    1.68
    Pool
    1.66
    Activations Density 0.354%

    No Known Activations