© 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. 1-RES-SM
    11. 26227
    Prev
    Next
    INDEX
    Explanations

    references to hospitality and leisure facilities

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.24
    1.4%
    56
    +0.16
    1.0%
    288
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.24
    0.11
    56
    +0.16
    -0.02
    288
    +0.13
    0.09
    Negative Logits
    ĥ½
    -4.42
    ·
    -4.39
    ¤
    -4.23
    Ĵ
    -4.20
    ¥
    -4.03
    ĸ
    -4.03
    «
    -4.00
    ¾
    -3.99
    §
    -3.98
    Ĥ
    -3.96
    POSITIVE LOGITS
    holder
    1.82
     featured
    1.78
     enclosure
    1.74
     adjo
    1.72
     coordinator
    1.70
     hosted
    1.67
     interior
    1.62
     featuring
    1.60
     Villa
    1.60
     chair
    1.56
    Activations Density 2.109%

    No Known Activations