© 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. 23860
    Prev
    Next
    INDEX
    Explanations

    measurements and dimensions related to physical objects

    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
    157
    +0.16
    0.9%
    84
    +0.13
    0.7%
    102
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.20
    271
    +0.13
    0.08
    156
    +0.13
    0.09
    Negative Logits
    ®
    -2.20
    ĻĤ
    -2.10
    ³
    -2.09
    ²
    -2.08
    ©
    -2.04
    ¦
    -1.92
     backdrop
    -1.89
    §
    -1.87
    ĥ
    -1.81
    Ľ
    -1.78
    POSITIVE LOGITS
    8859
    1.57
    romycin
    1.53
    icode
    1.47
    nio
    1.43
     restaurants
    1.42
     WARRANTY
    1.41
    pec
    1.41
    javase
    1.37
    quito
    1.34
    æĪ·
    1.34
    Activations Density 0.300%

    No Known Activations