© 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. 15344
    Prev
    Next
    INDEX
    Explanations

    sections that provide examples, tips, and instructions

    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
    307
    +0.23
    1.3%
    306
    +0.15
    0.9%
    240
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.23
    0.12
    156
    +0.15
    0.13
    274
    +0.11
    0.13
    Negative Logits
    »¿
    -1.64
    ģ
    -1.57
    ĥ
    -1.52
    idase
    -1.52
    ^/
    -1.51
    Ķ
    -1.50
    ^+^
    -1.47
    dimethyl
    -1.47
    uler
    -1.42
     oxidase
    -1.39
    POSITIVE LOGITS
     excerpt
    2.58
     directions
    2.54
     overview
    2.44
     highlights
    2.42
     details
    2.39
     descriptions
    2.38
     detailed
    2.31
     instructions
    2.28
     tips
    2.24
     examples
    2.21
    Activations Density 2.152%

    No Known Activations