© 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. 4-RES-SM
    11. 13944
    Prev
    Next
    INDEX
    Explanations

    references to various types of media and their attributes

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    348
    +0.14
    0.8%
    400
    +0.13
    0.8%
    307
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.22
    156
    +0.13
    0.22
    25
    +0.12
    0.18
    Negative Logits
    pancy
    -1.58
    arcoma
    -1.56
    ){#
    -1.53
    hower
    -1.48
    vette
    -1.48
    ggle
    -1.47
    agogue
    -1.46
    hift
    -1.46
    uvre
    -1.42
    ymp
    -1.39
    POSITIVE LOGITS
    isms
    2.80
     sizes
    2.77
    sets
    2.77
    es
    2.76
    izations
    2.75
    ages
    2.74
    ties
    2.72
    ents
    2.67
     configurations
    2.66
     assemblies
    2.66
    Activations Density 2.652%

    No Known Activations