© 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. 28349
    Prev
    Next
    INDEX
    Explanations

    instances of the word "interesting" in various contexts

    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
    +0.14
    0.8%
    376
    +0.14
    0.8%
    489
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.14
    0.04
    489
    +0.14
    0.03
    36
    +0.13
    0.03
    Negative Logits
    icates
    -1.86
    ene
    -1.66
     âī¤
    -1.59
    ulose
    -1.58
    enne
    -1.55
    anie
    -1.51
    ridge
    -1.51
    ower
    -1.48
    iferase
    -1.46
    ows
    -1.43
    POSITIVE LOGITS
    ly
    2.22
    looking
    1.89
    ty
    1.73
    ¿½
    1.70
    noreply
    1.64
     short
    1.62
    ness
    1.61
    istically
    1.59
     huh
    1.58
    ky
    1.54
    Activations Density 0.159%

    No Known Activations