© 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. 4-RES-SM
    11. 11225
    Prev
    Next
    INDEX
    Explanations

    concepts and expressions associated with enjoyment and amusement

    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
    274
    +0.14
    0.8%
    181
    +0.13
    0.7%
    361
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.03
    41
    +0.13
    0.03
    263
    +0.12
    0.04
    Negative Logits
    upon
    -2.03
     hardness
    -1.68
     respective
    -1.64
     corresponding
    -1.57
     sufficiency
    -1.55
     suitability
    -1.54
     adequacy
    -1.53
     thickness
    -1.50
    ridge
    -1.50
    ARRANT
    -1.50
    POSITIVE LOGITS
    nier
    3.04
    erals
    2.98
    ky
    2.95
    ni
    2.60
    ktion
    2.33
    ny
    2.32
    nel
    2.29
    nest
    2.18
    ¿½
    2.17
    icular
    2.16
    Activations Density 0.463%

    No Known Activations