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

    Neuronpedia

    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. 11774
    Prev
    Next
    INDEX
    Explanations

    terms related to laser technology and its applications

    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
    148
    +0.17
    1.0%
    348
    +0.14
    0.8%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.17
    0.01
    148
    +0.14
    0.01
    443
    +0.12
    0.02
    Negative Logits
    ĻĤ
    -2.46
    §
    -1.99
    ¹
    -1.90
    ľĵ
    -1.86
    fasterxml
    -1.82
    iary
    -1.76
    ĥ
    -1.72
    Ŀ
    -1.71
    ercase
    -1.70
    ¨
    -1.67
    POSITIVE LOGITS
     beam
    2.40
     irradiation
    2.20
     beams
    2.17
     ablation
    2.13
     diodes
    2.08
     diode
    2.07
    beam
    2.03
    shot
    1.93
     scanning
    1.92
     cutter
    1.86
    Activations Density 0.108%

    No Known Activations