© 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. 8993
    Prev
    Next
    INDEX
    Explanations

    proper nouns and references to specific individuals or characters

    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
    466
    +0.19
    1.1%
    348
    +0.17
    1.0%
    78
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.19
    0.04
    410
    +0.17
    0.06
    166
    +0.16
    0.05
    Negative Logits
    tons
    -1.63
    gence
    -1.55
    TING
    -1.48
    matic
    -1.45
    documentclass
    -1.43
    mable
    -1.37
    so
    -1.35
     day
    -1.33
    ting
    -1.33
    ted
    -1.31
    POSITIVE LOGITS
    §
    2.62
    »¿
    2.49
    «
    2.38
         ↵
    2.23
    <|outofrange|>
    2.23
    ↵
    2.23
    Â
    2.23
    2.23
    2.23
    ↵↵
    2.23
    Activations Density 1.266%

    No Known Activations