© 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. 28766
    Prev
    Next
    INDEX
    Explanations

    references to harmful or detrimental behaviors and ideologies

    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
    407
    +0.14
    0.8%
    377
    +0.13
    0.8%
    322
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.14
    0.02
    322
    +0.13
    0.02
    337
    +0.12
    0.02
    Negative Logits
    soever
    -2.41
    izumab
    -1.99
    upon
    -1.83
    abouts
    -1.70
    hores
    -1.54
    geant
    -1.42
    eer
    -1.42
     PROFITS
    -1.41
    abil
    -1.39
    sis
    -1.39
    POSITIVE LOGITS
    ³
    2.29
    ·¸
    2.25
    ļ
    2.23
    Ĵ
    2.16
    Ľ
    2.07
    Ķ
    2.04
    ı
    2.00
    Ĭ
    1.92
    Ĩ
    1.90
    Ī
    1.85
    Activations Density 0.068%

    No Known Activations