© 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. 10647
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to file configurations and system setups

    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
    156
    +0.29
    1.9%
    21
    +0.16
    1.0%
    397
    +0.15
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.29
    0.11
    17
    +0.16
    0.09
    78
    +0.15
    0.00
    Negative Logits
    ald
    -1.45
    iors
    -1.44
     regard
    -1.40
    ctrine
    -1.32
    enium
    -1.32
    than
    -1.27
     fleet
    -1.26
    ableness
    -1.25
     respect
    -1.22
     utmost
    -1.20
    POSITIVE LOGITS
    =${
    2.31
    =%
    2.11
    ="${
    2.08
    =#
    1.91
    ="'
    1.85
    =\"
    1.79
    ={
    1.72
    ="$
    1.70
    =$(
    1.70
    ='
    1.65
    Activations Density 1.512%

    No Known Activations