© 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. 27658
    Prev
    Next
    INDEX
    Explanations

    expressions related to enjoyment and entertainment

    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
    74
    +0.12
    0.6%
    458
    +0.11
    0.6%
    41
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.12
    0.03
    112
    +0.11
    0.03
    458
    +0.11
    0.02
    Negative Logits
    º
    -1.81
    ı
    -1.78
    »
    -1.77
    ħ
    -1.76
    Ĩ
    -1.76
    ĻĤ
    -1.71
     Redistributions
    -1.68
    ij
    -1.68
    Ļ
    -1.68
    upon
    -1.65
    POSITIVE LOGITS
    erals
    2.86
    ktion
    1.92
    nel
    1.89
    icular
    1.84
    imation
    1.82
    ky
    1.75
    nier
    1.74
    ctors
    1.73
    istically
    1.71
    ct
    1.70
    Activations Density 0.167%

    No Known Activations