© 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. 1-RES-SM
    11. 26348
    Prev
    Next
    INDEX
    Explanations

    references to various types of schemes or programs, particularly in a formal context

    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
    +0.20
    1.1%
    194
    +0.12
    0.7%
    483
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.20
    0.02
    483
    +0.12
    0.01
    264
    +0.12
    0.01
    Negative Logits
     tears
    -1.80
     awful
    -1.65
    jours
    -1.62
     shame
    -1.62
     awhile
    -1.61
     somebody
    -1.59
     guts
    -1.56
     happier
    -1.55
     dignity
    -1.51
     bitterly
    -1.49
    POSITIVE LOGITS
    ochrom
    1.67
    warz
    1.61
    imetry
    1.61
    Īĺ
    1.59
    pec
    1.58
    sover
    1.52
    names
    1.51
     diagram
    1.50
    generator
    1.49
     appears
    1.47
    Activations Density 0.102%

    No Known Activations