© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23988
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and places

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.12
    0.7%
    23
    +0.12
    0.7%
    105
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    -0.03
    418
    +0.12
    0.01
    23
    +0.12
    0.11
    Negative Logits
    ij
    -1.70
     ([@
    -1.63
    forge
    -1.62
    jections
    -1.54
     themselves
    -1.53
     andere
    -1.50
    wine
    -1.50
    license
    -1.45
     \[[@
    -1.43
    lei
    -1.42
    POSITIVE LOGITS
     caption
    1.72
     overtime
    1.64
    ably
    1.59
     congressional
    1.46
    ť
    1.40
     its
    1.40
     bipartisan
    1.39
     Congressional
    1.39
    mid
    1.36
     hurricane
    1.35
    Activations Density 2.575%

    No Known Activations