© 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. 2-RES-SM
    11. 31541
    Prev
    Next
    INDEX
    Explanations

    references to photography and photo-related terms

    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
    +0.14
    0.8%
    148
    +0.13
    0.8%
    203
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.14
    0.01
    477
    +0.13
    0.02
    386
    +0.13
    0.01
    Negative Logits
     respect
    -1.68
     seriousness
    -1.67
    erce
    -1.56
    aliana
    -1.55
    hip
    -1.54
    lament
    -1.52
    ETHOD
    -1.50
    stant
    -1.50
    lain
    -1.49
    versed
    -1.49
    POSITIVE LOGITS
    obi
    1.49
    ographs
    1.48
    ¦
    1.47
    ette
    1.46
    oshop
    1.45
     films
    1.44
    etimes
    1.42
    jpeg
    1.41
    oelectric
    1.41
    oby
    1.39
    Activations Density 0.081%

    No Known Activations