© 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. 1-RES-SM
    11. 26500
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial concepts

    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
    265
    +0.14
    0.8%
    369
    +0.14
    0.8%
    48
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    265
    +0.14
    0.12
    368
    +0.14
    0.07
    48
    +0.11
    0.10
    Negative Logits
    Ļª
    -1.75
    ĭ
    -1.58
    iber
    -1.47
     cardiomyopathy
    -1.44
    ichte
    -1.43
     fancy
    -1.41
    ange
    -1.40
    icht
    -1.40
    dden
    -1.32
    avor
    -1.31
    POSITIVE LOGITS
     portion
    1.66
     Greeks
    1.65
     YOU
    1.62
     implication
    1.54
    relationship
    1.51
     counterpart
    1.51
     itself
    1.49
     thing
    1.44
     situation
    1.42
    sequences
    1.42
    Activations Density 2.662%

    No Known Activations