© 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. 1-RES-SM
    11. 24638
    Prev
    Next
    INDEX
    Explanations

    sequences related to questions and answers in discussions or interviews

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    331
    +0.13
    0.7%
    66
    +0.12
    0.6%
    235
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.13
    0.05
    294
    +0.12
    0.03
    150
    +0.10
    0.05
    Negative Logits
    pite
    -1.97
    HECK
    -1.61
    xit
    -1.58
    rapy
    -1.54
    than
    -1.49
    uses
    -1.49
    wards
    -1.47
    cdots
    -1.46
    terday
    -1.42
     sins
    -1.42
    POSITIVE LOGITS
    £
    2.79
    ¡
    2.64
    ¢
    2.57
    ĻĤ
    2.54
    ĸ
    2.49
    ĨĴ
    2.43
    ¹
    2.35
    «
    2.30
    ¥
    2.29
    ħ
    2.26
    Activations Density 0.868%

    No Known Activations