© 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 EvalsExportsinterp-engineNEWAPI 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. 24870
    Prev
    Next
    INDEX
    Explanations

    prepositions and their uses in context

    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
    304
    +0.12
    0.6%
    94
    +0.11
    0.6%
    319
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.12
    0.00
    225
    +0.11
    0.00
    324
    +0.11
    0.00
    Negative Logits
    ¼
    -2.32
    Ĵ
    -2.21
    ľĵ
    -1.96
    µ
    -1.96
    ²
    -1.91
    Ŀ
    -1.80
    ¤
    -1.77
    ĺ
    -1.73
    į
    -1.69
    ķ
    -1.67
    POSITIVE LOGITS
    PING
    1.63
     encoding
    1.56
    athe
    1.49
    áĢº
    1.44
     accret
    1.40
    inherit
    1.40
    ('./
    1.39
     Transmission
    1.37
    oral
    1.36
     Expression
    1.36
    Activations Density 0.001%

    No Known Activations