© 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. 10242
    Prev
    Next
    INDEX
    Explanations

    phrases indicating surprise or disbelief

    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
    306
    +0.25
    1.5%
    307
    +0.20
    1.2%
    490
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.25
    0.08
    11
    +0.20
    0.08
    410
    +0.12
    0.08
    Negative Logits
     hereinafter
    -1.64
    ,[@
    -1.52
    ,^[@
    -1.49
     hereafter
    -1.43
    ystems
    -1.40
    )](#
    -1.40
     (§
    -1.40
    sembl
    -1.39
     Annex
    -1.32
     adjacent
    -1.31
    POSITIVE LOGITS
    pecially
    2.02
    actly
    1.92
    ruly
    1.91
    alking
    1.81
    uitively
    1.78
    ought
    1.73
    aaaa
    1.71
    ipping
    1.71
    ired
    1.68
    aying
    1.62
    Activations Density 0.843%

    No Known Activations