© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12201
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to liability and defenses

    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
    504
    +0.14
    0.9%
    281
    +0.10
    0.7%
    232
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.14
    0.00
    334
    +0.10
    0.03
    329
    +0.10
    0.03
    Negative Logits
    ļ
    -2.10
    ³
    -1.98
    »¿
    -1.93
    ¶
    -1.80
    ĻĤ
    -1.78
    ĸ´
    -1.77
    ·
    -1.76
    ĨĴ
    -1.76
    ī
    -1.74
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.74
    POSITIVE LOGITS
    suppl
    1.38
    ени
    1.34
    ение
    1.31
    hed
    1.28
    ---|
    1.28
    ---|---
    1.26
    ODY
    1.24
    bars
    1.23
    itin
    1.22
    ениÑı
    1.22
    Activations Density 0.375%

    No Known Activations