© 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. 30080
    Prev
    Next
    INDEX
    Explanations

    phrases related to video player status and feedback regarding video protection

    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
    368
    +0.11
    0.6%
    40
    +0.11
    0.6%
    236
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.11
    0.08
    329
    +0.11
    0.04
    463
    +0.11
    0.05
    Negative Logits
    ĩ
    -2.61
    ĥ½
    -2.50
    »¿
    -2.48
    Į
    -2.38
    ↵↵
    -2.35
    -2.35
    ↵
    -2.35
    č↵
    -2.35
    -2.35
    -2.35
    POSITIVE LOGITS
    .").
    1.99
    .");
    1.91
    ....
    1.87
    ...."
    1.81
    ?).
    1.81
    ????
    1.79
    .?
    1.71
    ))?
    1.70
    ??
    1.68
    ???
    1.67
    Activations Density 4.614%

    No Known Activations