© 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. 9304
    Prev
    Next
    INDEX
    Explanations

    URLs and command structures related to digital content management

    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
    78
    +0.16
    0.9%
    27
    +0.12
    0.7%
    331
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.16
    0.05
    78
    +0.12
    0.01
    27
    +0.10
    0.07
    Negative Logits
    ĻĤ
    -2.53
    ↵
    -2.25
    -2.25
    -2.25
    ↵
    -2.25
     ↵
    -2.25
    -2.25
    ↵
    -2.25
     ↵
    -2.25
    -2.25
    POSITIVE LOGITS
    =
    4.70
    =-
    4.00
    =[
    3.84
    =/
    3.78
    *=
    3.76
    =&
    3.61
    =.
    3.56
    =%
    3.51
    =(
    3.50
    ={
    3.48
    Activations Density 0.616%

    No Known Activations