© 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. 2-RES-SM
    11. 26661
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or statistical data

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    350
    +0.15
    0.8%
    369
    +0.12
    0.7%
    304
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.15
    0.03
    350
    +0.12
    0.03
    445
    +0.11
    0.02
    Negative Logits
    chie
    -1.51
    operative
    -1.45
    lem
    -1.44
    izable
    -1.43
    herent
    -1.42
     history
    -1.37
    ftware
    -1.36
     contra
    -1.34
     presentation
    -1.33
     unavailable
    -1.32
    POSITIVE LOGITS
    ĥ½
    2.42
    ³
    2.31
    ¾
    2.14
    ĺ
    2.12
    ¨
    2.05
    ®
    2.03
    st
    1.96
    ľ
    1.83
    Ĵ
    1.81
    ·
    1.80
    Activations Density 0.120%

    No Known Activations