© 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. 13804
    Prev
    Next
    INDEX
    Explanations

    specific dates and numbers related to events

    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
    397
    +0.14
    0.8%
    445
    +0.12
    0.6%
    392
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.14
    0.03
    238
    +0.12
    0.01
    142
    +0.11
    0.02
    Negative Logits
    ights
    -1.83
    ulated
    -1.82
    iates
    -1.73
    iating
    -1.67
    ftware
    -1.65
    chaft
    -1.64
    shire
    -1.61
    arians
    -1.58
    akers
    -1.57
    ESULT
    -1.54
    POSITIVE LOGITS
    st
    4.21
    âģĦ
    2.73
    Ľ
    2.65
    ¸
    2.54
    ĩ
    2.43
    ¤
    2.43
    ·
    2.42
    ¨
    2.38
    Ŀ
    2.36
    ŀ
    2.28
    Activations Density 0.260%

    No Known Activations