© 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. 11865
    Prev
    Next
    INDEX
    Explanations

    structured code snippets or formatting elements

    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
    455
    +0.16
    0.9%
    78
    +0.16
    0.9%
    348
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.16
    0.02
    461
    +0.16
    0.04
    78
    +0.13
    0.00
    Negative Logits
     venue
    -1.44
    thy
    -1.42
     seat
    -1.41
     Presidential
    -1.32
     homeostasis
    -1.31
     Rica
    -1.29
     Estados
    -1.28
     Metropolitan
    -1.28
     justice
    -1.26
    aukee
    -1.25
    POSITIVE LOGITS
    ¼
    4.32
    Ļ
    4.18
    ľĵ
    4.18
    ¤
    4.17
    į
    4.12
    «
    4.09
    ı
    4.08
    Į
    4.01
    ij
    4.01
    ĸ
    3.99
    Activations Density 0.361%

    No Known Activations