© 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. 25723
    Prev
    Next
    INDEX
    Explanations

    terms related to gastrointestinal issues or 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/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
    174
    +0.16
    0.9%
    243
    +0.13
    0.8%
    111
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.02
    174
    +0.13
    0.01
    271
    +0.13
    -0.00
    Negative Logits
     hers
    -1.95
    etermined
    -1.54
     tragedy
    -1.52
     tears
    -1.50
    ital
    -1.49
     mourning
    -1.49
     loud
    -1.49
     yours
    -1.48
    iful
    -1.46
    ('<
    -1.45
    POSITIVE LOGITS
    ³
    3.19
    Ľ
    3.07
    Ī
    2.82
    ·¸
    2.76
    ĻĤ
    2.72
    ī
    2.68
    ¤
    2.68
    ĭ
    2.60
    ¡
    2.56
    £
    2.55
    Activations Density 0.097%

    No Known Activations