© 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 EvalsExportsAPI 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. 27337
    Prev
    Next
    INDEX
    Explanations

    medical terms related to abdominal and digestive health

    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
    +0.21
    1.2%
    443
    +0.11
    0.6%
    51
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.21
    0.05
    156
    +0.11
    0.03
    271
    +0.10
    0.01
    Negative Logits
     everyone
    -1.78
     everybody
    -1.68
    ocratic
    -1.65
     yours
    -1.65
     respectful
    -1.64
    aneously
    -1.64
     happening
    -1.63
     precious
    -1.58
     gentle
    -1.58
     suppose
    -1.56
    POSITIVE LOGITS
    µ
    2.71
    Ľ
    2.44
    Ĺ
    2.26
    ī
    2.16
    Ł
    2.16
    ĻĤ
    2.15
    į
    2.13
    ¢
    2.12
    ·¸
    2.08
    £
    2.07
    Activations Density 0.126%

    No Known Activations