© 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. 2-RES-SM
    11. 10471
    Prev
    Next
    INDEX
    Explanations

    references to aqueous solutions and their characteristics

    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
    +0.17
    1.0%
    144
    +0.11
    0.6%
    47
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    465
    +0.17
    0.04
    392
    +0.11
    0.03
    47
    +0.10
    0.04
    Negative Logits
    §
    -3.30
    ŀ
    -2.98
    Ħ
    -2.92
    Ĵ
    -2.92
    ¾
    -2.88
    ¦
    -2.84
    ļ
    -2.83
    ±
    -2.82
    ĸ
    -2.80
    ĵ
    -2.75
    POSITIVE LOGITS
    assay
    2.01
     obtained
    2.00
     containing
    1.95
    ect
    1.92
     purified
    1.91
    ément
    1.86
    ankton
    1.80
    hemat
    1.78
     assayed
    1.75
     smelled
    1.72
    Activations Density 0.278%

    No Known Activations