© 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. 2-RES-SM
    11. 30682
    Prev
    Next
    INDEX
    Explanations

    terms related to gastric and intestinal health conditions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.20
    1.2%
    173
    +0.13
    0.8%
    12
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.20
    0.02
    148
    +0.13
    0.01
    468
    +0.12
    0.01
    Negative Logits
    eting
    -2.06
    edes
    -1.62
    arily
    -1.59
    fully
    -1.49
     realistic
    -1.47
     Photoshop
    -1.47
     hands
    -1.46
    arching
    -1.46
    andals
    -1.44
    boards
    -1.43
    POSITIVE LOGITS
    Ń
    3.31
    ĻĤ
    3.29
    Į
    3.27
    Ĩ
    3.23
    ¨
    3.20
    µ
    3.17
    £
    3.14
    ³
    3.10
    ª
    3.08
    ł
    3.07
    Activations Density 0.050%

    No Known Activations