© 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. 1-RES-SM
    11. 29494
    Prev
    Next
    INDEX
    Explanations

    code-related terms and variable types

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.39
    2.3%
    17
    +0.15
    0.9%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.39
    0.06
    218
    +0.15
    0.06
    210
    +0.14
    0.05
    Negative Logits
     \[
    -1.60
    :"
    -1.40
    :"){
    -1.37
     doi
    -1.34
    isenberg
    -1.33
    :")
    -1.32
    âĢħ
    -1.32
    isch
    -1.26
    idem
    -1.26
    *:
    -1.25
    POSITIVE LOGITS
    spir
    1.40
    ingly
    1.39
     streak
    1.38
    uities
    1.35
    ously
    1.34
    ĻĤ
    1.34
    grades
    1.33
    omorphic
    1.33
    uous
    1.32
     minds
    1.30
    Activations Density 0.304%

    No Known Activations