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

    Neuronpedia

    Jacobian LensNEW
    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. 28847
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to user login and authentication processes

    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
    156
    +0.27
    1.5%
    281
    +0.11
    0.7%
    45
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.27
    0.01
    45
    +0.11
    0.01
    17
    +0.11
    0.00
    Negative Logits
    Ĭ
    -2.40
    ´
    -2.29
    Ļ
    -2.19
    IJ
    -1.97
    -1.95
    -1.95
    ↵    ↵
    -1.95
     ↵
    -1.95
    ↵        ↵
    -1.95
    ↵
    -1.95
    POSITIVE LOGITS
     credentials
    1.99
    ership
    1.93
     mistake
    1.75
     notification
    1.71
     controller
    1.70
     service
    1.67
     experience
    1.65
     server
    1.59
     realm
    1.57
     opportunity
    1.57
    Activations Density 0.174%

    No Known Activations