© 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. 11642
    Prev
    Next
    INDEX
    Explanations

    articles and quantifiers that indicate various qualities or descriptions

    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
    141
    +0.14
    0.8%
    156
    +0.14
    0.8%
    391
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.14
    0.06
    436
    +0.14
    0.06
    145
    +0.12
    0.05
    Negative Logits
    ±
    -2.19
    à±ģ
    -2.05
    «
    -1.94
    à¯ģ
    -1.91
    ½
    -1.88
    ankton
    -1.88
    ãģ¹
    -1.80
    ĻĤ
    -1.77
     heels
    -1.75
    Į
    -1.74
    POSITIVE LOGITS
     opportunity
    2.29
     glimpse
    2.27
     insight
    2.17
     chance
    2.08
     basis
    2.04
     convenient
    2.03
     possibility
    1.96
     clue
    1.91
     flexibility
    1.90
     warning
    1.86
    Activations Density 0.562%

    No Known Activations