© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25872
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sn" in various contexts, likely indicating a focus on expressions of humor or laughter

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    369
    +0.15
    0.9%
    59
    +0.15
    0.9%
    410
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.15
    0.03
    144
    +0.15
    0.03
    172
    +0.13
    0.02
    Negative Logits
    cles
    -1.78
     ÃĤ
    -1.69
    undy
    -1.61
    ]>
    -1.54
     HREF
    -1.54
    rese
    -1.53
    mente
    -1.48
     ↵
    -1.46
    umi
    -1.45
    ments
    -1.45
    POSITIVE LOGITS
    itzer
    1.86
    ippets
    1.67
     exception
    1.56
     anthem
    1.56
    chez
    1.53
    acking
    1.44
     drafted
    1.41
    eller
    1.40
    ty
    1.40
     crafted
    1.37
    Activations Density 0.107%

    No Known Activations