© 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. 24336
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory requirements and compliance

    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
    386
    +0.14
    0.8%
    372
    +0.13
    0.8%
    332
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.14
    0.06
    285
    +0.13
    0.06
    11
    +0.12
    0.05
    Negative Logits
    manship
    -1.72
    chus
    -1.63
     wonders
    -1.61
    ahoma
    -1.58
    za
    -1.52
    waukee
    -1.51
    abouts
    -1.46
    ano
    -1.39
     town
    -1.39
    ubot
    -1.38
    POSITIVE LOGITS
    ABLE
    1.64
    LECT
    1.60
    ensible
    1.52
    orter
    1.46
    JECT
    1.45
    ers
    1.37
    IGNED
    1.36
    izable
    1.35
    icted
    1.34
    utable
    1.32
    Activations Density 0.854%

    No Known Activations