© 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. 13938
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, especially those describing ongoing or chronic issues

    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
    +0.19
    1.1%
    304
    +0.14
    0.8%
    30
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.19
    0.01
    304
    +0.14
    0.04
    246
    +0.12
    0.04
    Negative Logits
    že
    -1.89
    iah
    -1.60
    ashed
    -1.49
    aband
    -1.48
    room
    -1.48
    ave
    -1.47
    CRO
    -1.46
    ounge
    -1.44
    ž
    -1.44
    asse
    -1.43
    POSITIVE LOGITS
    ļ
    4.08
    ł
    4.01
    Ĵ
    3.91
    ·¸
    3.79
    ij
    3.78
    ľĵ
    3.67
    ±
    3.66
    £
    3.65
    ³
    3.59
    ¨
    3.50
    Activations Density 0.229%

    No Known Activations