© 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. 28616
    Prev
    Next
    INDEX
    Explanations

    imperative verbs indicating actions or functions

    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
    485
    +0.13
    0.7%
    130
    +0.12
    0.7%
    387
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    485
    +0.13
    0.06
    387
    +0.12
    0.06
    173
    +0.12
    0.06
    Negative Logits
    Ļª
    -3.12
    ĨĴ
    -3.04
    ¼
    -2.75
    ij
    -2.68
    ¡
    -2.54
    £
    -2.53
    ŀ
    -2.38
    µ
    -2.21
    ĻĤ
    -2.20
    »¿
    -2.17
    POSITIVE LOGITS
    pez
    2.05
    zens
    2.05
    xy
    1.87
    zed
    1.86
    xygen
    1.85
    ž
    1.82
    zin
    1.80
    olev
    1.78
    oming
    1.75
    ppler
    1.73
    Activations Density 0.196%

    No Known Activations