© 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. 29255
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and associated standards in the context of various fields

    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
    111
    +0.18
    1.0%
    23
    +0.16
    0.9%
    478
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.28
    271
    +0.16
    0.13
    156
    +0.15
    0.13
    Negative Logits
    lei
    -1.62
    inyl
    -1.50
     faint
    -1.49
     synthesized
    -1.44
    imer
    -1.42
     itself
    -1.39
     digit
    -1.39
     fain
    -1.38
    urus
    -1.36
    isl
    -1.35
    POSITIVE LOGITS
     our
    1.76
     ours
    1.49
    rench
    1.42
     mankind
    1.38
     mine
    1.34
     conservation
    1.34
    cdot
    1.32
    equiv
    1.31
     racism
    1.29
     yours
    1.29
    Activations Density 0.324%

    No Known Activations