© 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. 13938
    Prev
    Next
    INDEX
    Explanations

    prepositions and their usage within sentences

    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
    307
    +0.37
    2.2%
    274
    +0.17
    1.0%
    306
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.37
    0.13
    306
    +0.17
    0.07
    69
    +0.13
    0.09
    Negative Logits
    .
    -1.91
    .*;
    -1.74
    .[^
    -1.71
    ^.
    -1.71
    .",
    -1.68
    ){#
    -1.63
    .[
    -1.61
    .^\[[@
    -1.57
    **.
    -1.56
    _.
    -1.56
    POSITIVE LOGITS
    Ń
    3.88
    ↵
    3.73
    ↵↵
    3.73
    <|outofrange|>
    3.73
    ↵
    3.73
    ↵
    3.73
    č↵
    3.73
    3.73
    3.73
    3.73
    Activations Density 1.278%

    No Known Activations