© 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. 4-RES-SM
    11. 9916
    Prev
    Next
    INDEX
    Explanations

    references to the word "swamp."

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    410
    +0.16
    0.9%
    271
    +0.14
    0.8%
    371
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.16
    0.03
    371
    +0.14
    0.03
    373
    +0.12
    0.02
    Negative Logits
     Parenthood
    -1.65
     child
    -1.55
    ncia
    -1.54
    aries
    -1.53
     lieu
    -1.52
     course
    -1.51
     chance
    -1.49
    hood
    -1.47
    orems
    -1.42
    itory
    -1.41
    POSITIVE LOGITS
    Ģ
    3.36
    Ĵ
    3.32
    Ļ
    3.11
    IJ
    3.05
    Ħ
    3.02
    ª
    2.98
    ²
    2.93
    ¬
    2.84
    ij
    2.83
    ¡
    2.79
    Activations Density 0.061%

    No Known Activations