© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    references to specific numbers, particularly the number seventeen

    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
    46
    +0.13
    0.7%
    369
    +0.12
    0.7%
    412
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.13
    0.03
    69
    +0.12
    0.04
    393
    +0.12
    0.02
    Negative Logits
    ://
    -1.84
    verse
    -1.77
    "}](#
    -1.77
    usp
    -1.65
    vers
    -1.60
    ories
    -1.58
    manifest
    -1.44
     mechanics
    -1.40
    gered
    -1.40
     versa
    -1.39
    POSITIVE LOGITS
    ¾
    4.00
    ħ
    3.68
    µ
    3.59
    ·¸
    3.42
    ĥ½
    3.36
    ³
    3.29
    ²
    3.27
    ®
    3.26
    ¥
    3.15
    Ľ
    3.11
    Activations Density 0.163%

    No Known Activations