© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27315
    Prev
    Next
    INDEX
    Explanations

    references to drug use and addiction-related terms

    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
    156
    +0.20
    1.1%
    271
    +0.16
    0.9%
    186
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.20
    0.00
    32
    +0.16
    0.04
    2
    +0.15
    0.05
    Negative Logits
     Doppler
    -1.65
     hyste
    -1.64
    ighs
    -1.64
    IRST
    -1.56
    ftime
    -1.56
     confocal
    -1.55
     Hubble
    -1.55
    acent
    -1.52
     graduation
    -1.51
     EXPECT
    -1.50
    POSITIVE LOGITS
    ł
    2.06
    ¸
    1.98
    ĥ
    1.98
    ī
    1.91
    IJ
    1.89
    ħ
    1.87
    ¹
    1.87
    Ķ
    1.78
    º
    1.77
    ¥
    1.77
    Activations Density 0.781%

    No Known Activations