© 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. 12648
    Prev
    Next
    INDEX
    Explanations

    events and activities related to social gatherings or performances

    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
    262
    +0.14
    0.8%
    263
    +0.11
    0.6%
    288
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.14
    0.05
    262
    +0.11
    0.06
    145
    +0.10
    0.08
    Negative Logits
    ¢
    -2.21
    ĩ
    -2.07
    ģ
    -1.93
    Ĩ
    -1.93
    į
    -1.92
    ¶
    -1.90
    nabla
    -1.89
    ·¸
    -1.85
    Ķ
    -1.83
    İ
    -1.79
    POSITIVE LOGITS
     attendees
    4.03
     festival
    3.66
     attendance
    3.58
     organizers
    3.42
     concerts
    3.37
     Tickets
    3.29
     exhib
    3.28
     Festival
    3.25
     spectators
    3.23
     venue
    3.19
    Activations Density 4.248%

    No Known Activations