© 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. 4-RES-SM
    11. 10202
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Of" in various contexts

    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
    314
    +0.11
    0.6%
    478
    +0.10
    0.6%
    282
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.11
    0.03
    314
    +0.10
    0.03
    139
    +0.10
    0.03
    Negative Logits
     before
    -1.77
    ocyt
    -1.49
     vacated
    -1.48
    ites
    -1.45
     without
    -1.43
     of
    -1.42
     oxidase
    -1.42
    icum
    -1.41
    ")
    -1.39
    izumab
    -1.37
    POSITIVE LOGITS
     course
    3.74
    fered
    3.23
    course
    2.73
     necessity
    2.29
    sted
    2.12
     Mice
    2.04
     note
    1.99
     particular
    1.92
    stood
    1.92
     Course
    1.81
    Activations Density 0.174%

    No Known Activations