© 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. 29056
    Prev
    Next
    INDEX
    Explanations

    words related to the topic of agriculture or crop production

    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
    283
    +0.12
    0.7%
    220
    +0.12
    0.7%
    5
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.12
    0.01
    509
    +0.12
    0.02
    386
    +0.11
    0.01
    Negative Logits
    hip
    -1.78
    antly
    -1.74
    hips
    -1.68
    lessly
    -1.59
     await
    -1.58
    ance
    -1.58
     "$
    -1.58
     parties
    -1.52
     "*
    -1.48
     entire
    -1.46
    POSITIVE LOGITS
    oulos
    1.85
    ème
    1.78
    ublic
    1.71
    onte
    1.65
    nell
    1.65
    igt
    1.61
    icture
    1.60
    onent
    1.59
    seud
    1.58
    ings
    1.58
    Activations Density 0.100%

    No Known Activations