© 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. 2-RES-SM
    11. 30648
    Prev
    Next
    INDEX
    Explanations

    frequent adverbs and expressions indicating regularity or emphasis in actions

    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
    289
    +0.13
    0.7%
    23
    +0.13
    0.7%
    386
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.13
    0.04
    386
    +0.13
    0.03
    288
    +0.13
    0.07
    Negative Logits
    ptions
    -2.29
    »
    -2.12
    ĻĤ
    -2.08
    IGENCE
    -2.07
    ption
    -1.97
    ª
    -1.92
    IES
    -1.85
    İ
    -1.83
    ĭ
    -1.81
    ATIONS
    -1.80
    POSITIVE LOGITS
     hers
    1.80
     grateful
    1.74
     appreciated
    1.59
     ashamed
    1.58
     okay
    1.57
     theirs
    1.56
    ).](
    1.51
    likely
    1.50
     ours
    1.50
    olated
    1.49
    Activations Density 0.536%

    No Known Activations