© 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. 32263
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to programming and configuration management

    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
    47
    +0.19
    1.1%
    419
    +0.14
    0.8%
    186
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.19
    0.10
    417
    +0.14
    0.10
    47
    +0.14
    0.18
    Negative Logits
     families
    -1.56
    }})$
    -1.45
    ei
    -1.43
    acre
    -1.42
     Families
    -1.41
     Welfare
    -1.39
     Foundation
    -1.37
    idis
    -1.37
    utta
    -1.36
    itage
    -1.35
    POSITIVE LOGITS
    ¹
    2.79
    ľĵ
    2.68
    Īĺ
    2.53
    ĭ
    2.47
    º
    2.46
    ²
    2.45
    ı
    2.43
    Ł
    2.39
    ¼
    2.38
    ¶
    2.35
    Activations Density 8.682%

    No Known Activations