© 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. 12412
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific legal disclaimers and warranties

    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
    111
    +0.13
    0.7%
    98
    +0.11
    0.6%
    494
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.13
    0.03
    347
    +0.11
    0.03
    116
    +0.11
    0.03
    Negative Logits
    lessly
    -1.99
     included
    -1.69
     desk
    -1.59
     acuity
    -1.46
    fully
    -1.41
     includes
    -1.39
    fulness
    -1.38
     respected
    -1.38
    Of
    -1.37
     overruled
    -1.37
    POSITIVE LOGITS
    «
    3.29
    Ń
    3.05
    §
    3.00
    ĥ
    2.92
    Ģ
    2.81
    ¡
    2.67
    ¯
    2.64
    ľ
    2.63
    ¢
    2.62
    Ļª
    2.61
    Activations Density 0.407%

    No Known Activations