© 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. 4-RES-SM
    11. 13144
    Prev
    Next
    INDEX
    Explanations

    words related to data analysis or formatting concerns

    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
    423
    +0.16
    0.9%
    364
    +0.12
    0.7%
    26
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.25
    156
    +0.12
    0.20
    71
    +0.11
    0.17
    Negative Logits
     Cain
    -2.00
     tribe
    -1.98
     canoe
    -1.95
     bikes
    -1.87
     Torres
    -1.80
     cruiser
    -1.78
     TAG
    -1.73
     policing
    -1.73
    chains
    -1.73
     wrestling
    -1.72
    POSITIVE LOGITS
     Excel
    3.80
    Excel
    3.79
     excel
    3.35
     spreadsheet
    3.15
    Sheet
    2.88
    sheet
    2.79
     Sheet
    2.76
    xl
    2.70
     sheet
    2.68
     csv
    2.59
    Activations Density 0.999%

    No Known Activations