© 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. 8758
    Prev
    Next
    INDEX
    Explanations

    specific betting terms and related references

    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
    91
    +0.13
    0.7%
    70
    +0.13
    0.7%
    306
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.13
    0.04
    410
    +0.13
    0.03
    166
    +0.11
    0.03
    Negative Logits
    itating
    -1.64
    iencies
    -1.61
    ingly
    -1.60
     infra
    -1.59
    atter
    -1.56
    QUE
    -1.53
    ately
    -1.52
    ensus
    -1.49
    Ŀ
    -1.48
    itate
    -1.48
    POSITIVE LOGITS
    оÑĢм
    1.92
    ray
    1.79
    rays
    1.72
    à±
    1.70
    Ñĥн
    1.63
    amethasone
    1.58
    ield
    1.55
    ricks
    1.52
    à±ģ
    1.47
    ãĤ£
    1.45
    Activations Density 0.468%

    No Known Activations