© 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. 4-RES-SM
    11. 15305
    Prev
    Next
    INDEX
    Explanations

    words associated with blight or decay, particularly in a metaphorical context

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    477
    +0.13
    0.7%
    397
    +0.12
    0.7%
    62
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.13
    0.03
    303
    +0.12
    0.03
    62
    +0.12
    0.02
    Negative Logits
     themselves
    -1.70
    ional
    -1.69
     right
    -1.60
    ocratic
    -1.59
     itself
    -1.58
    thon
    -1.58
    rias
    -1.48
    rin
    -1.47
    abine
    -1.43
    ophageal
    -1.41
    POSITIVE LOGITS
    uetooth
    2.28
    izzard
    2.06
    ĨĴ
    1.93
    uffs
    1.87
    urbs
    1.78
    azing
    1.74
    itzer
    1.73
    urb
    1.72
    anco
    1.71
    unders
    1.69
    Activations Density 0.050%

    No Known Activations