© 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. 29160
    Prev
    Next
    INDEX
    Explanations

    references to winners or winning in various contexts

    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
    +0.15
    0.9%
    73
    +0.15
    0.8%
    351
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.15
    0.03
    351
    +0.15
    0.03
    290
    +0.13
    0.02
    Negative Logits
    ĥ½
    -2.26
    ij
    -2.12
    ĵ
    -2.04
    ĺ
    -2.01
    ĻĤ
    -1.90
    ´
    -1.88
    ŀ
    -1.86
    «
    -1.83
    ·
    -1.83
    ¿½
    -1.80
    POSITIVE LOGITS
    bucks
    1.69
     streak
    1.68
    doms
    1.64
     laps
    1.60
     lottery
    1.54
    pole
    1.53
     stre
    1.49
    ger
    1.49
    nesday
    1.48
    abouts
    1.48
    Activations Density 0.200%

    No Known Activations