© 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. 1-RES-SM
    11. 27173
    Prev
    Next
    INDEX
    Explanations

    phrases involving participation in various activities or events

    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
    +0.21
    1.2%
    69
    +0.15
    0.8%
    68
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.21
    0.08
    64
    +0.15
    0.03
    186
    +0.12
    -0.00
    Negative Logits
    ®
    -1.61
    ström
    -1.58
    tons
    -1.54
     palate
    -1.52
    dimen
    -1.52
    fonts
    -1.45
    еÑģк
    -1.43
    stdio
    -1.43
    limits
    -1.42
    Ł
    -1.37
    POSITIVE LOGITS
     participating
    1.66
     full
    1.66
     Participants
    1.55
     planned
    1.53
     any
    1.48
    party
    1.46
    shore
    1.45
     simulated
    1.45
     party
    1.44
     recruitment
    1.43
    Activations Density 0.873%

    No Known Activations