© 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. 2-RES-SM
    11. 28297
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Tom" 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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.17
    1.0%
    369
    +0.17
    0.9%
    410
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.17
    0.04
    59
    +0.17
    0.02
    369
    +0.15
    0.02
    Negative Logits
     association
    -1.74
     case
    -1.71
    Docket
    -1.64
    semin
    -1.62
     ours
    -1.61
    VERTISEMENT
    -1.58
    requency
    -1.57
    ERTYPE
    -1.55
    ferenced
    -1.53
    TES
    -1.49
    POSITIVE LOGITS
    atoes
    2.42
    ©
    2.13
    ī
    2.03
    ±
    1.98
    ¸
    1.97
    ¹
    1.94
    ½
    1.91
    pson
    1.90
    ankind
    1.84
    Ĭ
    1.83
    Activations Density 0.129%

    No Known Activations