© 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. 32085
    Prev
    Next
    INDEX
    Explanations

    programming-related commands and terms

    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
    419
    +0.20
    1.2%
    436
    +0.16
    0.9%
    369
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.20
    0.05
    369
    +0.16
    0.03
    419
    +0.15
    0.05
    Negative Logits
     surprise
    -1.72
    noreply
    -1.56
    angs
    -1.53
     Yard
    -1.41
    ientes
    -1.37
    ales
    -1.36
    uity
    -1.31
     Morning
    -1.31
     inhibitory
    -1.29
    eric
    -1.28
    POSITIVE LOGITS
    PROTO
    1.67
    ubuntu
    1.63
     visibility
    1.48
    ¾
    1.44
    going
    1.44
    ¿
    1.44
    Ľ
    1.43
    ½
    1.42
    emptyset
    1.41
    ®
    1.40
    Activations Density 0.482%

    No Known Activations