© 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. 2-RES-SM
    11. 30085
    Prev
    Next
    INDEX
    Explanations

    content related to greetings and welcoming statements

    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
    410
    +0.16
    0.9%
    108
    +0.14
    0.8%
    473
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.16
    0.02
    148
    +0.14
    0.00
    38
    +0.13
    0.01
    Negative Logits
    İ
    -2.94
    §
    -2.93
    ¯
    -2.87
    ĥ½
    -2.62
    Ļ
    -2.58
    į
    -2.58
    ©
    -2.57
    ĵ
    -2.54
    ³
    -2.54
    ¹
    -2.49
    POSITIVE LOGITS
     guests
    1.73
     volunteers
    1.72
    opan
    1.64
     sponsors
    1.61
     posters
    1.60
    ETHOD
    1.60
     visitors
    1.59
     newcom
    1.57
     commentary
    1.53
     clarification
    1.49
    Activations Density 0.313%

    No Known Activations