© 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. 2-RES-SM
    11. 32457
    Prev
    Next
    INDEX
    Explanations

    elements related to code structure and organization

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.18
    1.0%
    326
    +0.17
    1.0%
    21
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.18
    0.10
    25
    +0.17
    0.13
    27
    +0.13
    0.09
    Negative Logits
     ?
    -1.44
     cref
    -1.42
     them
    -1.39
     accordingly
    -1.31
    azz
    -1.30
    )?
    -1.30
     Crick
    -1.29
     remarks
    -1.23
    ities
    -1.21
    ison
    -1.21
    POSITIVE LOGITS
    Ļ
    2.36
    Ĩ
    2.27
    ¿
    2.25
    Ŀ
    2.22
    ¾
    2.22
    ĻĤ
    2.18
    ħ
    2.08
    °
    2.07
    Ģ
    2.04
    ®
    2.03
    Activations Density 3.737%

    No Known Activations