© 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. 13228
    Prev
    Next
    INDEX
    Explanations

    phrases related to inclusion and representation

    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
    400
    +0.18
    1.0%
    186
    +0.13
    0.7%
    78
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.33
    156
    +0.13
    0.32
    71
    +0.12
    0.32
    Negative Logits
    itably
    -1.91
    ationally
    -1.77
    ulously
    -1.69
    entially
    -1.66
    astically
    -1.60
    utively
    -1.58
    arily
    -1.57
    idone
    -1.53
    antically
    -1.52
    ically
    -1.52
    POSITIVE LOGITS
    ção
    1.60
     exist
    1.49
    ees
    1.46
     exists
    1.31
    ÃŃs
    1.29
     narrative
    1.28
     thesis
    1.27
     Explorer
    1.27
     compilation
    1.26
     Waters
    1.26
    Activations Density 4.184%

    No Known Activations