© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 29898
    Prev
    Next
    INDEX
    Explanations

    words related to addiction recovery and rehabilitation

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    182
    +0.13
    0.7%
    250
    +0.13
    0.7%
    348
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.13
    0.01
    250
    +0.13
    0.02
    182
    +0.12
    0.01
    Negative Logits
     alarm
    -1.73
     clear
    -1.72
     obvious
    -1.66
     focus
    -1.65
     going
    -1.60
     coloured
    -1.58
     toast
    -1.56
     remembering
    -1.53
     temper
    -1.52
     growing
    -1.51
    POSITIVE LOGITS
    ĻĤ
    2.28
    ĥ½
    2.27
    »
    2.09
    endra
    1.97
    ressor
    1.93
    ¹
    1.90
    ¤
    1.89
    itat
    1.86
    icans
    1.86
    ¸
    1.85
    Activations Density 0.098%

    No Known Activations