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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 11398
    Prev
    Next
    INDEX
    Explanations

    references to "infidelity."

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.13
    0.8%
    322
    +0.13
    0.7%
    118
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.13
    0.01
    322
    +0.13
    0.01
    501
    +0.12
    0.01
    Negative Logits
    izumab
    -1.92
    soever
    -1.78
    abouts
    -1.68
    heed
    -1.62
    sis
    -1.62
    upon
    -1.59
    abil
    -1.54
     eds
    -1.52
    geant
    -1.49
    tics
    -1.48
    POSITIVE LOGITS
    ³
    2.20
    ļ
    2.17
    Ĭ
    2.01
    Ĵ
    1.94
    ŀ
    1.93
    ·¸
    1.88
    Ķ
    1.84
    Ĩ
    1.81
    ł
    1.79
    ı
    1.79
    Activations Density 0.116%

    No Known Activations