© 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. 2-RES-SM
    11. 28421
    Prev
    Next
    INDEX
    Explanations

    statements related to disclaimers and opinions regarding health information

    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
    294
    +0.18
    1.0%
    302
    +0.14
    0.8%
    456
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.18
    0.06
    103
    +0.14
    0.09
    302
    +0.13
    0.09
    Negative Logits
    ĨĴ
    -3.05
    ľĵ
    -2.87
    ¯
    -2.75
    ķ
    -2.58
    ®
    -2.57
    Ļª
    -2.57
    »¿
    -2.56
    Īĺ
    -2.52
    ĥ
    -2.47
    ı
    -2.44
    POSITIVE LOGITS
     copyrighted
    2.01
     confidentiality
    1.96
     confidential
    1.87
     endorsement
    1.87
     written
    1.83
     disclaim
    1.82
    written
    1.80
     consent
    1.75
     harmless
    1.73
    ureus
    1.72
    Activations Density 2.940%

    No Known Activations