© 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. 13394
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer hardware and performance metrics

    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
    +0.15
    0.9%
    152
    +0.13
    0.7%
    397
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.15
    0.02
    17
    +0.13
    0.00
    446
    +0.13
    0.02
    Negative Logits
    ¼
    -3.54
    ³
    -3.43
    ĥ½
    -3.31
    ł
    -3.16
    º
    -2.97
    Ħ
    -2.87
    ĥ
    -2.86
    ¿½
    -2.80
    ¯
    -2.79
    ¾
    -2.77
    POSITIVE LOGITS
    itecture
    2.13
     computing
    2.07
     speeds
    1.95
     Computing
    1.92
     architectures
    1.89
     cores
    1.83
     accelerator
    1.83
     architecture
    1.79
    GPU
    1.78
     capabilities
    1.75
    Activations Density 0.381%

    No Known Activations