© 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. 1-RES-SM
    11. 26640
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the arrival or release of something new

    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
    447
    +0.12
    0.6%
    351
    +0.10
    0.6%
    178
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.12
    0.03
    405
    +0.10
    0.03
    178
    +0.10
    0.03
    Negative Logits
    §
    -4.34
    ĥ½
    -4.25
    ĻĤ
    -4.09
    ¢
    -3.89
    Ń
    -3.78
    ĺ
    -3.77
    ¡
    -3.75
    ī
    -3.72
    Ī
    -3.71
    ľ
    -3.69
    POSITIVE LOGITS
     back
    1.84
    fires
    1.84
     together
    1.69
     closer
    1.64
    fire
    1.63
     forth
    1.61
    Soon
    1.61
     suddenly
    1.55
     hither
    1.52
     alive
    1.52
    Activations Density 0.151%

    No Known Activations