© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13552
    Prev
    Next
    INDEX
    Explanations

    contractions indicating possession or identity

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.18
    1.0%
    378
    +0.13
    0.7%
    420
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.18
    0.04
    331
    +0.13
    0.04
    89
    +0.13
    0.03
    Negative Logits
    İ
    -3.60
    ł
    -3.54
    ļ
    -3.52
    Ĺ
    -3.50
    ¤
    -3.21
    ŀ
    -3.20
    ı
    -3.11
    ¡
    -3.03
    Ģ
    -3.02
    ľ
    -3.01
    POSITIVE LOGITS
     gotten
    2.39
     forgotten
    2.18
     prefer
    2.17
     recommend
    2.14
     happier
    1.98
     been
    1.97
     gladly
    1.96
     regret
    1.93
     hoped
    1.93
     sworn
    1.82
    Activations Density 0.119%

    No Known Activations