© 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. 23870
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specialization or expertise in various fields

    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
    300
    +0.15
    0.8%
    198
    +0.14
    0.8%
    23
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.15
    0.02
    300
    +0.14
    0.05
    418
    +0.13
    0.01
    Negative Logits
    /~
    -2.04
    /)
    -1.93
    ĨĴ
    -1.92
    ³
    -1.77
    ¶
    -1.74
    Ģ
    -1.69
    ↵³³
    -1.68
    leneck
    -1.67
    ovo
    -1.56
    ¾
    -1.55
    POSITIVE LOGITS
    esium
    1.58
    ylene
    1.44
    ETHOD
    1.40
     probes
    1.38
    selves
    1.38
     roles
    1.35
     Areas
    1.35
     regards
    1.32
     diagnoses
    1.32
    iencies
    1.31
    Activations Density 0.574%

    No Known Activations