© 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 EvalsExportsinterp-engineNEWAPI 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. 28277
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming and gambling

    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
    156
    +0.18
    1.0%
    282
    +0.15
    0.9%
    230
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.18
    0.05
    282
    +0.15
    0.05
    173
    +0.14
    0.04
    Negative Logits
    ľ
    -2.85
    ī
    -2.53
    Ŀ
    -2.53
    ĥ½
    -2.45
    ĺ
    -2.38
    »
    -2.33
    Į
    -2.31
    ij
    -2.31
    ·
    -2.29
    İ
    -2.27
    POSITIVE LOGITS
    apore
    2.24
     grounds
    2.01
    redients
    1.87
    roup
    1.82
    ulator
    1.79
     services
    1.73
     establishments
    1.72
     enthusi
    1.68
     purposes
    1.67
    ulate
    1.64
    Activations Density 0.273%

    No Known Activations