© 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. 4-RES-SM
    11. 10902
    Prev
    Next
    INDEX
    Explanations

    terms related to software availability and licensing conditions

    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
    271
    +0.14
    0.8%
    0
    +0.10
    0.6%
    348
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.14
    0.02
    334
    +0.10
    0.01
    172
    +0.09
    0.02
    Negative Logits
    ters
    -1.43
     yourself
    -1.42
    ifice
    -1.36
     epithelium
    -1.30
     manag
    -1.29
    ting
    -1.28
     sket
    -1.26
     populated
    -1.24
    ation
    -1.23
     Dra
    -1.21
    POSITIVE LOGITS
    ŀ
    3.42
    ¿
    3.32
    ²
    3.21
    ¹
    3.18
    Ļª
    3.16
    Ī
    3.15
    ¼
    3.15
    Ĵ
    3.15
    ³
    3.14
    Ŀ
    3.13
    Activations Density 0.089%

    No Known Activations