© 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. 28795
    Prev
    Next
    INDEX
    Explanations

    references to specific bacteria and medical terms related to gastrointestinal 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
    111
    +0.15
    0.8%
    397
    +0.15
    0.8%
    167
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.02
    321
    +0.15
    0.01
    370
    +0.12
    0.01
    Negative Logits
     learning
    -1.76
     lots
    -1.60
     board
    -1.55
     stitches
    -1.51
     thumbs
    -1.46
     feet
    -1.42
     glad
    -1.42
     somebody
    -1.41
     inches
    -1.41
    fully
    -1.40
    POSITIVE LOGITS
    iral
    1.97
    enberg
    1.87
    resis
    1.82
    untime
    1.69
    acker
    1.60
    dom
    1.59
    ugu
    1.57
    pective
    1.57
    ISPR
    1.54
    lander
    1.53
    Activations Density 0.068%

    No Known Activations