© 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. 25072
    Prev
    Next
    INDEX
    Explanations

    phrases related to illegal activities or violations of laws and ethical standards

    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
    156
    +0.28
    1.6%
    308
    +0.11
    0.6%
    476
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.28
    0.01
    326
    +0.11
    0.03
    501
    +0.11
    0.02
    Negative Logits
    ilda
    -1.53
     careful
    -1.50
    cha
    -1.47
    whel
    -1.43
    rils
    -1.41
    chitz
    -1.40
    ching
    -1.40
    rend
    -1.40
    kins
    -1.39
    yla
    -1.35
    POSITIVE LOGITS
    ĻĤ
    2.75
    ·
    2.40
    Ł
    2.29
    ²
    2.04
    º
    2.02
    ĸ
    1.99
    ¥
    1.94
    ½
    1.92
    ¤
    1.84
    Ľ
    1.83
    Activations Density 0.210%

    No Known Activations