© 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. 32019
    Prev
    Next
    INDEX
    Explanations

    references to Agile methodologies and concepts

    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
    369
    +0.14
    0.8%
    74
    +0.12
    0.7%
    443
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.14
    0.02
    203
    +0.12
    0.02
    59
    +0.12
    0.01
    Negative Logits
    aintiff
    -1.85
    TRODUCTION
    -1.65
    acht
    -1.56
     shortest
    -1.52
    puted
    -1.48
     adjustable
    -1.42
    disambiguation
    -1.39
     pupil
    -1.38
    ferentially
    -1.38
    cludes
    -1.38
    POSITIVE LOGITS
    ŀ
    2.81
    Ĵ
    2.77
    ±
    2.70
    ļ
    2.67
    ĸ
    2.49
    ¦
    2.46
    º
    2.45
    ĩ
    2.42
    ©
    2.39
    ¹
    2.38
    Activations Density 0.093%

    No Known Activations